From f42c9026f5a88bc5a60b07ca03544e6d97226197 Mon Sep 17 00:00:00 2001 From: Adriane Boyd Date: Mon, 29 Jun 2020 14:13:12 +0200 Subject: [PATCH] Update v2.3.x branch (#5636) * Fix typos and auto-format [ci skip] * Add pkuseg warnings and auto-format [ci skip] * Update Binder URL [ci skip] * Update Binder version [ci skip] * Update alignment example for new gold.align * Update POS in tagging example * Fix numpy.zeros() dtype for Doc.from_array * Change example title to Dr. Change example title to Dr. so the current model does exclude the title in the initial example. * Fix spacy convert argument * Warning for sudachipy 0.4.5 (#5611) * Create myavrum.md (#5612) * Update lex_attrs.py (#5608) * Create mahnerak.md (#5615) * Some changes for Armenian (#5616) * Fixing numericals * We need a Armenian question sign to make the sentence a question * Add Nepali Language (#5622) * added support for nepali lang * added examples and test files * added spacy contributor agreement * Japanese model: add user_dict entries and small refactor (#5573) * user_dict fields: adding inflections, reading_forms, sub_tokens deleting: unidic_tags improve code readability around the token alignment procedure * add test cases, replace fugashi with sudachipy in conftest * move bunsetu.py to spaCy Universe as a pipeline component BunsetuRecognizer * tag is space -> both surface and tag are spaces * consider len(text)==0 * Add warnings example in v2.3 migration guide (#5627) * contribute (#5632) * Fix polarity of Token.is_oov and Lexeme.is_oov (#5634) Fix `Token.is_oov` and `Lexeme.is_oov` so they return `True` when the lexeme does **not** have a vector. * Extend what's new in v2.3 with vocab / is_oov (#5635) * Skip vocab in component config overrides (#5624) * Fix backslashes in warnings config diff (#5640) Fix backslashes in warnings config diff in v2.3 migration section. * Disregard special tag _SP in check for new tag map (#5641) * Skip special tag _SP in check for new tag map In `Tagger.begin_training()` check for new tags aside from `_SP` in the new tag map initialized from the provided gold tuples when determining whether to reinitialize the morphology with the new tag map. * Simplify _SP check Co-authored-by: Ines Montani Co-authored-by: Marat M. Yavrumyan Co-authored-by: Karen Hambardzumyan Co-authored-by: Rameshh <30867740+rameshhpathak@users.noreply.github.com> Co-authored-by: Hiroshi Matsuda <40782025+hiroshi-matsuda-rit@users.noreply.github.com> Co-authored-by: Richard Liaw --- .github/contributors/mahnerak.md | 106 +++++ .github/contributors/myavrum.md | 106 +++++ .github/contributors/rameshhpathak.md | 106 +++++ .github/contributors/richardliaw.md | 106 +++++ spacy/lang/hy/examples.py | 2 +- spacy/lang/hy/lex_attrs.py | 25 +- spacy/lang/ja/__init__.py | 203 +++++---- spacy/lang/ja/bunsetu.py | 144 ------- spacy/lang/ne/__init__.py | 23 + spacy/lang/ne/examples.py | 22 + spacy/lang/ne/lex_attrs.py | 98 +++++ spacy/lang/ne/stop_words.py | 498 ++++++++++++++++++++++ spacy/lexeme.pyx | 2 +- spacy/pipeline/pipes.pyx | 4 +- spacy/tests/conftest.py | 5 + spacy/tests/lang/ja/test_tokenizer.py | 53 ++- spacy/tests/lang/ne/__init__.py | 0 spacy/tests/lang/ne/test_text.py | 19 + spacy/tests/pipeline/test_tagger.py | 14 + spacy/tests/vocab_vectors/test_vectors.py | 6 +- spacy/tokens/token.pyx | 2 +- spacy/util.py | 4 + website/docs/api/goldparse.md | 49 +-- website/docs/api/matcher.md | 2 +- website/docs/usage/101/_pos-deps.md | 2 +- website/docs/usage/adding-languages.md | 2 +- website/docs/usage/linguistic-features.md | 8 +- website/docs/usage/models.md | 24 +- website/docs/usage/rule-based-matching.md | 12 +- website/docs/usage/v2-3.md | 172 +++++--- website/meta/site.json | 4 +- 31 files changed, 1458 insertions(+), 365 deletions(-) create mode 100644 .github/contributors/mahnerak.md create mode 100644 .github/contributors/myavrum.md create mode 100644 .github/contributors/rameshhpathak.md create mode 100644 .github/contributors/richardliaw.md delete mode 100644 spacy/lang/ja/bunsetu.py create mode 100644 spacy/lang/ne/__init__.py create mode 100644 spacy/lang/ne/examples.py create mode 100644 spacy/lang/ne/lex_attrs.py create mode 100644 spacy/lang/ne/stop_words.py create mode 100644 spacy/tests/lang/ne/__init__.py create mode 100644 spacy/tests/lang/ne/test_text.py diff --git a/.github/contributors/mahnerak.md b/.github/contributors/mahnerak.md new file mode 100644 index 000000000..cc7739681 --- /dev/null +++ b/.github/contributors/mahnerak.md @@ -0,0 +1,106 @@ +# spaCy contributor agreement + +This spaCy Contributor Agreement (**"SCA"**) is based on the +[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf). +The SCA applies to any contribution that you make to any product or project +managed by us (the **"project"**), and sets out the intellectual property rights +you grant to us in the contributed materials. The term **"us"** shall mean +[ExplosionAI GmbH](https://explosion.ai/legal). The term +**"you"** shall mean the person or entity identified below. + +If you agree to be bound by these terms, fill in the information requested +below and include the filled-in version with your first pull request, under the +folder [`.github/contributors/`](/.github/contributors/). The name of the file +should be your GitHub username, with the extension `.md`. For example, the user +example_user would create the file `.github/contributors/example_user.md`. + +Read this agreement carefully before signing. These terms and conditions +constitute a binding legal agreement. + +## Contributor Agreement + +1. The term "contribution" or "contributed materials" means any source code, +object code, patch, tool, sample, graphic, specification, manual, +documentation, or any other material posted or submitted by you to the project. + +2. With respect to any worldwide copyrights, or copyright applications and +registrations, in your contribution: + + * you hereby assign to us joint ownership, and to the extent that such + assignment is or becomes invalid, ineffective or unenforceable, you hereby + grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge, + royalty-free, unrestricted license to exercise all rights under those + copyrights. This includes, at our option, the right to sublicense these same + rights to third parties through multiple levels of sublicensees or other + licensing arrangements; + + * you agree that each of us can do all things in relation to your + contribution as if each of us were the sole owners, and if one of us makes + a derivative work of your contribution, the one who makes the derivative + work (or has it made will be the sole owner of that derivative work; + + * you agree that you will not assert any moral rights in your contribution + against us, our licensees or transferees; + + * you agree that we may register a copyright in your contribution and + exercise all ownership rights associated with it; and + + * you agree that neither of us has any duty to consult with, obtain the + consent of, pay or render an accounting to the other for any use or + distribution of your contribution. + +3. With respect to any patents you own, or that you can license without payment +to any third party, you hereby grant to us a perpetual, irrevocable, +non-exclusive, worldwide, no-charge, royalty-free license to: + + * make, have made, use, sell, offer to sell, import, and otherwise transfer + your contribution in whole or in part, alone or in combination with or + included in any product, work or materials arising out of the project to + which your contribution was submitted, and + + * at our option, to sublicense these same rights to third parties through + multiple levels of sublicensees or other licensing arrangements. + +4. Except as set out above, you keep all right, title, and interest in your +contribution. The rights that you grant to us under these terms are effective +on the date you first submitted a contribution to us, even if your submission +took place before the date you sign these terms. + +5. You covenant, represent, warrant and agree that: + + * Each contribution that you submit is and shall be an original work of + authorship and you can legally grant the rights set out in this SCA; + + * to the best of your knowledge, each contribution will not violate any + third party's copyrights, trademarks, patents, or other intellectual + property rights; and + + * each contribution shall be in compliance with U.S. export control laws and + other applicable export and import laws. You agree to notify us if you + become aware of any circumstance which would make any of the foregoing + representations inaccurate in any respect. We may publicly disclose your + participation in the project, including the fact that you have signed the SCA. + +6. This SCA is governed by the laws of the State of California and applicable +U.S. Federal law. Any choice of law rules will not apply. + +7. Please place an “x” on one of the applicable statement below. Please do NOT +mark both statements: + + * [x] I am signing on behalf of myself as an individual and no other person + or entity, including my employer, has or will have rights with respect to my + contributions. + + * [ ] I am signing on behalf of my employer or a legal entity and I have the + actual authority to contractually bind that entity. + +## Contributor Details + +| Field | Entry | +|------------------------------- | -------------------- | +| Name | Karen Hambardzumyan | +| Company name (if applicable) | YerevaNN | +| Title or role (if applicable) | Researcher | +| Date | 2020-06-19 | +| GitHub username | mahnerak | +| Website (optional) | https://mahnerak.com/| diff --git a/.github/contributors/myavrum.md b/.github/contributors/myavrum.md new file mode 100644 index 000000000..dc8f1bb84 --- /dev/null +++ b/.github/contributors/myavrum.md @@ -0,0 +1,106 @@ +# spaCy contributor agreement + +This spaCy Contributor Agreement (**"SCA"**) is based on the +[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf). +The SCA applies to any contribution that you make to any product or project +managed by us (the **"project"**), and sets out the intellectual property rights +you grant to us in the contributed materials. The term **"us"** shall mean +[ExplosionAI GmbH](https://explosion.ai/legal). The term +**"you"** shall mean the person or entity identified below. + +If you agree to be bound by these terms, fill in the information requested +below and include the filled-in version with your first pull request, under the +folder [`.github/contributors/`](/.github/contributors/). The name of the file +should be your GitHub username, with the extension `.md`. For example, the user +example_user would create the file `.github/contributors/example_user.md`. + +Read this agreement carefully before signing. These terms and conditions +constitute a binding legal agreement. + +## Contributor Agreement + +1. The term "contribution" or "contributed materials" means any source code, +object code, patch, tool, sample, graphic, specification, manual, +documentation, or any other material posted or submitted by you to the project. + +2. With respect to any worldwide copyrights, or copyright applications and +registrations, in your contribution: + + * you hereby assign to us joint ownership, and to the extent that such + assignment is or becomes invalid, ineffective or unenforceable, you hereby + grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge, + royalty-free, unrestricted license to exercise all rights under those + copyrights. This includes, at our option, the right to sublicense these same + rights to third parties through multiple levels of sublicensees or other + licensing arrangements; + + * you agree that each of us can do all things in relation to your + contribution as if each of us were the sole owners, and if one of us makes + a derivative work of your contribution, the one who makes the derivative + work (or has it made will be the sole owner of that derivative work; + + * you agree that you will not assert any moral rights in your contribution + against us, our licensees or transferees; + + * you agree that we may register a copyright in your contribution and + exercise all ownership rights associated with it; and + + * you agree that neither of us has any duty to consult with, obtain the + consent of, pay or render an accounting to the other for any use or + distribution of your contribution. + +3. With respect to any patents you own, or that you can license without payment +to any third party, you hereby grant to us a perpetual, irrevocable, +non-exclusive, worldwide, no-charge, royalty-free license to: + + * make, have made, use, sell, offer to sell, import, and otherwise transfer + your contribution in whole or in part, alone or in combination with or + included in any product, work or materials arising out of the project to + which your contribution was submitted, and + + * at our option, to sublicense these same rights to third parties through + multiple levels of sublicensees or other licensing arrangements. + +4. Except as set out above, you keep all right, title, and interest in your +contribution. The rights that you grant to us under these terms are effective +on the date you first submitted a contribution to us, even if your submission +took place before the date you sign these terms. + +5. You covenant, represent, warrant and agree that: + + * Each contribution that you submit is and shall be an original work of + authorship and you can legally grant the rights set out in this SCA; + + * to the best of your knowledge, each contribution will not violate any + third party's copyrights, trademarks, patents, or other intellectual + property rights; and + + * each contribution shall be in compliance with U.S. export control laws and + other applicable export and import laws. You agree to notify us if you + become aware of any circumstance which would make any of the foregoing + representations inaccurate in any respect. We may publicly disclose your + participation in the project, including the fact that you have signed the SCA. + +6. This SCA is governed by the laws of the State of California and applicable +U.S. Federal law. Any choice of law rules will not apply. + +7. Please place an “x” on one of the applicable statement below. Please do NOT +mark both statements: + + * [x] I am signing on behalf of myself as an individual and no other person + or entity, including my employer, has or will have rights with respect to my + contributions. + + * [ ] I am signing on behalf of my employer or a legal entity and I have the + actual authority to contractually bind that entity. + +## Contributor Details + +| Field | Entry | +|------------------------------- | -------------------- | +| Name | Marat M. Yavrumyan | +| Company name (if applicable) | YSU, UD_Armenian Project | +| Title or role (if applicable) | Dr., Principal Investigator | +| Date | 2020-06-19 | +| GitHub username | myavrum | +| Website (optional) | http://armtreebank.yerevann.com/ | diff --git a/.github/contributors/rameshhpathak.md b/.github/contributors/rameshhpathak.md new file mode 100644 index 000000000..30a543307 --- /dev/null +++ b/.github/contributors/rameshhpathak.md @@ -0,0 +1,106 @@ +# spaCy contributor agreement + +This spaCy Contributor Agreement (**"SCA"**) is based on the +[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf). +The SCA applies to any contribution that you make to any product or project +managed by us (the **"project"**), and sets out the intellectual property rights +you grant to us in the contributed materials. The term **"us"** shall mean +[ExplosionAI GmbH](https://explosion.ai/legal). The term +**"you"** shall mean the person or entity identified below. + +If you agree to be bound by these terms, fill in the information requested +below and include the filled-in version with your first pull request, under the +folder [`.github/contributors/`](/.github/contributors/). The name of the file +should be your GitHub username, with the extension `.md`. For example, the user +example_user would create the file `.github/contributors/example_user.md`. + +Read this agreement carefully before signing. These terms and conditions +constitute a binding legal agreement. + +## Contributor Agreement + +1. The term "contribution" or "contributed materials" means any source code, +object code, patch, tool, sample, graphic, specification, manual, +documentation, or any other material posted or submitted by you to the project. + +2. With respect to any worldwide copyrights, or copyright applications and +registrations, in your contribution: + + * you hereby assign to us joint ownership, and to the extent that such + assignment is or becomes invalid, ineffective or unenforceable, you hereby + grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge, + royalty-free, unrestricted license to exercise all rights under those + copyrights. This includes, at our option, the right to sublicense these same + rights to third parties through multiple levels of sublicensees or other + licensing arrangements; + + * you agree that each of us can do all things in relation to your + contribution as if each of us were the sole owners, and if one of us makes + a derivative work of your contribution, the one who makes the derivative + work (or has it made will be the sole owner of that derivative work; + + * you agree that you will not assert any moral rights in your contribution + against us, our licensees or transferees; + + * you agree that we may register a copyright in your contribution and + exercise all ownership rights associated with it; and + + * you agree that neither of us has any duty to consult with, obtain the + consent of, pay or render an accounting to the other for any use or + distribution of your contribution. + +3. With respect to any patents you own, or that you can license without payment +to any third party, you hereby grant to us a perpetual, irrevocable, +non-exclusive, worldwide, no-charge, royalty-free license to: + + * make, have made, use, sell, offer to sell, import, and otherwise transfer + your contribution in whole or in part, alone or in combination with or + included in any product, work or materials arising out of the project to + which your contribution was submitted, and + + * at our option, to sublicense these same rights to third parties through + multiple levels of sublicensees or other licensing arrangements. + +4. Except as set out above, you keep all right, title, and interest in your +contribution. The rights that you grant to us under these terms are effective +on the date you first submitted a contribution to us, even if your submission +took place before the date you sign these terms. + +5. You covenant, represent, warrant and agree that: + + * Each contribution that you submit is and shall be an original work of + authorship and you can legally grant the rights set out in this SCA; + + * to the best of your knowledge, each contribution will not violate any + third party's copyrights, trademarks, patents, or other intellectual + property rights; and + + * each contribution shall be in compliance with U.S. export control laws and + other applicable export and import laws. You agree to notify us if you + become aware of any circumstance which would make any of the foregoing + representations inaccurate in any respect. We may publicly disclose your + participation in the project, including the fact that you have signed the SCA. + +6. This SCA is governed by the laws of the State of California and applicable +U.S. Federal law. Any choice of law rules will not apply. + +7. Please place an “x” on one of the applicable statement below. Please do NOT +mark both statements: + + * [x] I am signing on behalf of myself as an individual and no other person + or entity, including my employer, has or will have rights with respect to my + contributions. + + * [ ] I am signing on behalf of my employer or a legal entity and I have the + actual authority to contractually bind that entity. + +## Contributor Details + +| Field | Entry | +|------------------------------- | -------------------- | +| Name | Ramesh Pathak | +| Company name (if applicable) | Diyo AI | +| Title or role (if applicable) | AI Engineer | +| Date | June 21, 2020 | +| GitHub username | rameshhpathak | +| Website (optional) |rameshhpathak.github.io| | diff --git a/.github/contributors/richardliaw.md b/.github/contributors/richardliaw.md new file mode 100644 index 000000000..2af4ce840 --- /dev/null +++ b/.github/contributors/richardliaw.md @@ -0,0 +1,106 @@ +# spaCy contributor agreement + +This spaCy Contributor Agreement (**"SCA"**) is based on the +[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf). +The SCA applies to any contribution that you make to any product or project +managed by us (the **"project"**), and sets out the intellectual property rights +you grant to us in the contributed materials. The term **"us"** shall mean +[ExplosionAI GmbH](https://explosion.ai/legal). The term +**"you"** shall mean the person or entity identified below. + +If you agree to be bound by these terms, fill in the information requested +below and include the filled-in version with your first pull request, under the +folder [`.github/contributors/`](/.github/contributors/). The name of the file +should be your GitHub username, with the extension `.md`. For example, the user +example_user would create the file `.github/contributors/example_user.md`. + +Read this agreement carefully before signing. These terms and conditions +constitute a binding legal agreement. + +## Contributor Agreement + +1. The term "contribution" or "contributed materials" means any source code, +object code, patch, tool, sample, graphic, specification, manual, +documentation, or any other material posted or submitted by you to the project. + +2. With respect to any worldwide copyrights, or copyright applications and +registrations, in your contribution: + + * you hereby assign to us joint ownership, and to the extent that such + assignment is or becomes invalid, ineffective or unenforceable, you hereby + grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge, + royalty-free, unrestricted license to exercise all rights under those + copyrights. This includes, at our option, the right to sublicense these same + rights to third parties through multiple levels of sublicensees or other + licensing arrangements; + + * you agree that each of us can do all things in relation to your + contribution as if each of us were the sole owners, and if one of us makes + a derivative work of your contribution, the one who makes the derivative + work (or has it made will be the sole owner of that derivative work; + + * you agree that you will not assert any moral rights in your contribution + against us, our licensees or transferees; + + * you agree that we may register a copyright in your contribution and + exercise all ownership rights associated with it; and + + * you agree that neither of us has any duty to consult with, obtain the + consent of, pay or render an accounting to the other for any use or + distribution of your contribution. + +3. With respect to any patents you own, or that you can license without payment +to any third party, you hereby grant to us a perpetual, irrevocable, +non-exclusive, worldwide, no-charge, royalty-free license to: + + * make, have made, use, sell, offer to sell, import, and otherwise transfer + your contribution in whole or in part, alone or in combination with or + included in any product, work or materials arising out of the project to + which your contribution was submitted, and + + * at our option, to sublicense these same rights to third parties through + multiple levels of sublicensees or other licensing arrangements. + +4. Except as set out above, you keep all right, title, and interest in your +contribution. The rights that you grant to us under these terms are effective +on the date you first submitted a contribution to us, even if your submission +took place before the date you sign these terms. + +5. You covenant, represent, warrant and agree that: + + * Each contribution that you submit is and shall be an original work of + authorship and you can legally grant the rights set out in this SCA; + + * to the best of your knowledge, each contribution will not violate any + third party's copyrights, trademarks, patents, or other intellectual + property rights; and + + * each contribution shall be in compliance with U.S. export control laws and + other applicable export and import laws. You agree to notify us if you + become aware of any circumstance which would make any of the foregoing + representations inaccurate in any respect. We may publicly disclose your + participation in the project, including the fact that you have signed the SCA. + +6. This SCA is governed by the laws of the State of California and applicable +U.S. Federal law. Any choice of law rules will not apply. + +7. Please place an “x” on one of the applicable statement below. Please do NOT +mark both statements: + + * [x] I am signing on behalf of myself as an individual and no other person + or entity, including my employer, has or will have rights with respect to my + contributions. + + * [ ] I am signing on behalf of my employer or a legal entity and I have the + actual authority to contractually bind that entity. + +## Contributor Details + +| Field | Entry | +|------------------------------- | -------------------- | +| Name | Richard Liaw | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 06/22/2020 | +| GitHub username | richardliaw | +| Website (optional) | | \ No newline at end of file diff --git a/spacy/lang/hy/examples.py b/spacy/lang/hy/examples.py index 323f77b1c..8a00fd243 100644 --- a/spacy/lang/hy/examples.py +++ b/spacy/lang/hy/examples.py @@ -11,6 +11,6 @@ Example sentences to test spaCy and its language models. sentences = [ "Լոնդոնը Միացյալ Թագավորության մեծ քաղաք է։", "Ո՞վ է Ֆրանսիայի նախագահը։", - "Որն է Միացյալ Նահանգների մայրաքաղաքը։", + "Ո՞րն է Միացյալ Նահանգների մայրաքաղաքը։", "Ե՞րբ է ծնվել Բարաք Օբաման։", ] diff --git a/spacy/lang/hy/lex_attrs.py b/spacy/lang/hy/lex_attrs.py index 910625fb8..dea3c0e97 100644 --- a/spacy/lang/hy/lex_attrs.py +++ b/spacy/lang/hy/lex_attrs.py @@ -5,8 +5,8 @@ from ...attrs import LIKE_NUM _num_words = [ - "զրօ", - "մէկ", + "զրո", + "մեկ", "երկու", "երեք", "չորս", @@ -18,20 +18,21 @@ _num_words = [ "տասը", "տասնմեկ", "տասներկու", - "տասն­երեք", - "տասն­չորս", - "տասն­հինգ", - "տասն­վեց", - "տասն­յոթ", - "տասն­ութ", - "տասն­ինը", - "քսան" "երեսուն", + "տասներեք", + "տասնչորս", + "տասնհինգ", + "տասնվեց", + "տասնյոթ", + "տասնութ", + "տասնինը", + "քսան", + "երեսուն", "քառասուն", "հիսուն", - "վաթցսուն", + "վաթսուն", "յոթանասուն", "ութսուն", - "ինիսուն", + "իննսուն", "հարյուր", "հազար", "միլիոն", diff --git a/spacy/lang/ja/__init__.py b/spacy/lang/ja/__init__.py index a7ad0846e..fb8b9d7fe 100644 --- a/spacy/lang/ja/__init__.py +++ b/spacy/lang/ja/__init__.py @@ -20,12 +20,7 @@ from ... import util # Hold the attributes we need with convenient names -DetailedToken = namedtuple("DetailedToken", ["surface", "pos", "lemma"]) - -# Handling for multiple spaces in a row is somewhat awkward, this simplifies -# the flow by creating a dummy with the same interface. -DummyNode = namedtuple("DummyNode", ["surface", "pos", "lemma"]) -DummySpace = DummyNode(" ", " ", " ") +DetailedToken = namedtuple("DetailedToken", ["surface", "tag", "inf", "lemma", "reading", "sub_tokens"]) def try_sudachi_import(split_mode="A"): @@ -53,7 +48,7 @@ def try_sudachi_import(split_mode="A"): ) -def resolve_pos(orth, pos, next_pos): +def resolve_pos(orth, tag, next_tag): """If necessary, add a field to the POS tag for UD mapping. Under Universal Dependencies, sometimes the same Unidic POS tag can be mapped differently depending on the literal token or its context @@ -64,124 +59,77 @@ def resolve_pos(orth, pos, next_pos): # Some tokens have their UD tag decided based on the POS of the following # token. - # orth based rules - if pos[0] in TAG_ORTH_MAP: - orth_map = TAG_ORTH_MAP[pos[0]] + # apply orth based mapping + if tag in TAG_ORTH_MAP: + orth_map = TAG_ORTH_MAP[tag] if orth in orth_map: - return orth_map[orth], None + return orth_map[orth], None # current_pos, next_pos - # tag bi-gram mapping - if next_pos: - tag_bigram = pos[0], next_pos[0] + # apply tag bi-gram mapping + if next_tag: + tag_bigram = tag, next_tag if tag_bigram in TAG_BIGRAM_MAP: - bipos = TAG_BIGRAM_MAP[tag_bigram] - if bipos[0] is None: - return TAG_MAP[pos[0]][POS], bipos[1] + current_pos, next_pos = TAG_BIGRAM_MAP[tag_bigram] + if current_pos is None: # apply tag uni-gram mapping for current_pos + return TAG_MAP[tag][POS], next_pos # only next_pos is identified by tag bi-gram mapping else: - return bipos + return current_pos, next_pos - return TAG_MAP[pos[0]][POS], None + # apply tag uni-gram mapping + return TAG_MAP[tag][POS], None -# Use a mapping of paired punctuation to avoid splitting quoted sentences. -pairpunct = {'「':'」', '『': '』', '【': '】'} - - -def separate_sentences(doc): - """Given a doc, mark tokens that start sentences based on Unidic tags. - """ - - stack = [] # save paired punctuation - - for i, token in enumerate(doc[:-2]): - # Set all tokens after the first to false by default. This is necessary - # for the doc code to be aware we've done sentencization, see - # `is_sentenced`. - token.sent_start = (i == 0) - if token.tag_: - if token.tag_ == "補助記号-括弧開": - ts = str(token) - if ts in pairpunct: - stack.append(pairpunct[ts]) - elif stack and ts == stack[-1]: - stack.pop() - - if token.tag_ == "補助記号-句点": - next_token = doc[i+1] - if next_token.tag_ != token.tag_ and not stack: - next_token.sent_start = True - - -def get_dtokens(tokenizer, text): - tokens = tokenizer.tokenize(text) - words = [] - for ti, token in enumerate(tokens): - tag = '-'.join([xx for xx in token.part_of_speech()[:4] if xx != '*']) - inf = '-'.join([xx for xx in token.part_of_speech()[4:] if xx != '*']) - dtoken = DetailedToken( - token.surface(), - (tag, inf), - token.dictionary_form()) - if ti > 0 and words[-1].pos[0] == '空白' and tag == '空白': - # don't add multiple space tokens in a row - continue - words.append(dtoken) - - # remove empty tokens. These can be produced with characters like … that - # Sudachi normalizes internally. - words = [ww for ww in words if len(ww.surface) > 0] - return words - - -def get_words_lemmas_tags_spaces(dtokens, text, gap_tag=("空白", "")): +def get_dtokens_and_spaces(dtokens, text, gap_tag="空白"): + # Compare the content of tokens and text, first words = [x.surface for x in dtokens] if "".join("".join(words).split()) != "".join(text.split()): raise ValueError(Errors.E194.format(text=text, words=words)) - text_words = [] - text_lemmas = [] - text_tags = [] + + text_dtokens = [] text_spaces = [] text_pos = 0 # handle empty and whitespace-only texts if len(words) == 0: - return text_words, text_lemmas, text_tags, text_spaces + return text_dtokens, text_spaces elif len([word for word in words if not word.isspace()]) == 0: assert text.isspace() - text_words = [text] - text_lemmas = [text] - text_tags = [gap_tag] + text_dtokens = [DetailedToken(text, gap_tag, '', text, None, None)] text_spaces = [False] - return text_words, text_lemmas, text_tags, text_spaces - # normalize words to remove all whitespace tokens - norm_words, norm_dtokens = zip(*[(word, dtokens) for word, dtokens in zip(words, dtokens) if not word.isspace()]) - # align words with text - for word, dtoken in zip(norm_words, norm_dtokens): + return text_dtokens, text_spaces + + # align words and dtokens by referring text, and insert gap tokens for the space char spans + for word, dtoken in zip(words, dtokens): + # skip all space tokens + if word.isspace(): + continue try: word_start = text[text_pos:].index(word) except ValueError: raise ValueError(Errors.E194.format(text=text, words=words)) + + # space token if word_start > 0: w = text[text_pos:text_pos + word_start] - text_words.append(w) - text_lemmas.append(w) - text_tags.append(gap_tag) + text_dtokens.append(DetailedToken(w, gap_tag, '', w, None, None)) text_spaces.append(False) text_pos += word_start - text_words.append(word) - text_lemmas.append(dtoken.lemma) - text_tags.append(dtoken.pos) + + # content word + text_dtokens.append(dtoken) text_spaces.append(False) text_pos += len(word) + # poll a space char after the word if text_pos < len(text) and text[text_pos] == " ": text_spaces[-1] = True text_pos += 1 + + # trailing space token if text_pos < len(text): w = text[text_pos:] - text_words.append(w) - text_lemmas.append(w) - text_tags.append(gap_tag) + text_dtokens.append(DetailedToken(w, gap_tag, '', w, None, None)) text_spaces.append(False) - return text_words, text_lemmas, text_tags, text_spaces + + return text_dtokens, text_spaces class JapaneseTokenizer(DummyTokenizer): @@ -191,29 +139,78 @@ class JapaneseTokenizer(DummyTokenizer): self.tokenizer = try_sudachi_import(self.split_mode) def __call__(self, text): - dtokens = get_dtokens(self.tokenizer, text) + # convert sudachipy.morpheme.Morpheme to DetailedToken and merge continuous spaces + sudachipy_tokens = self.tokenizer.tokenize(text) + dtokens = self._get_dtokens(sudachipy_tokens) + dtokens, spaces = get_dtokens_and_spaces(dtokens, text) - words, lemmas, unidic_tags, spaces = get_words_lemmas_tags_spaces(dtokens, text) + # create Doc with tag bi-gram based part-of-speech identification rules + words, tags, inflections, lemmas, readings, sub_tokens_list = zip(*dtokens) if dtokens else [[]] * 6 + sub_tokens_list = list(sub_tokens_list) doc = Doc(self.vocab, words=words, spaces=spaces) - next_pos = None - for idx, (token, lemma, unidic_tag) in enumerate(zip(doc, lemmas, unidic_tags)): - token.tag_ = unidic_tag[0] - if next_pos: + next_pos = None # for bi-gram rules + for idx, (token, dtoken) in enumerate(zip(doc, dtokens)): + token.tag_ = dtoken.tag + if next_pos: # already identified in previous iteration token.pos = next_pos next_pos = None else: token.pos, next_pos = resolve_pos( token.orth_, - unidic_tag, - unidic_tags[idx + 1] if idx + 1 < len(unidic_tags) else None + dtoken.tag, + tags[idx + 1] if idx + 1 < len(tags) else None ) - # if there's no lemma info (it's an unk) just use the surface - token.lemma_ = lemma - doc.user_data["unidic_tags"] = unidic_tags + token.lemma_ = dtoken.lemma if dtoken.lemma else dtoken.surface + + doc.user_data["inflections"] = inflections + doc.user_data["reading_forms"] = readings + doc.user_data["sub_tokens"] = sub_tokens_list return doc + def _get_dtokens(self, sudachipy_tokens, need_sub_tokens=True): + sub_tokens_list = self._get_sub_tokens(sudachipy_tokens) if need_sub_tokens else None + dtokens = [ + DetailedToken( + token.surface(), # orth + '-'.join([xx for xx in token.part_of_speech()[:4] if xx != '*']), # tag + ','.join([xx for xx in token.part_of_speech()[4:] if xx != '*']), # inf + token.dictionary_form(), # lemma + token.reading_form(), # user_data['reading_forms'] + sub_tokens_list[idx] if sub_tokens_list else None, # user_data['sub_tokens'] + ) for idx, token in enumerate(sudachipy_tokens) if len(token.surface()) > 0 + # remove empty tokens which can be produced with characters like … that + ] + # Sudachi normalizes internally and outputs each space char as a token. + # This is the preparation for get_dtokens_and_spaces() to merge the continuous space tokens + return [ + t for idx, t in enumerate(dtokens) if + idx == 0 or + not t.surface.isspace() or t.tag != '空白' or + not dtokens[idx - 1].surface.isspace() or dtokens[idx - 1].tag != '空白' + ] + + def _get_sub_tokens(self, sudachipy_tokens): + if self.split_mode is None or self.split_mode == "A": # do nothing for default split mode + return None + + sub_tokens_list = [] # list of (list of list of DetailedToken | None) + for token in sudachipy_tokens: + sub_a = token.split(self.tokenizer.SplitMode.A) + if len(sub_a) == 1: # no sub tokens + sub_tokens_list.append(None) + elif self.split_mode == "B": + sub_tokens_list.append([self._get_dtokens(sub_a, False)]) + else: # "C" + sub_b = token.split(self.tokenizer.SplitMode.B) + if len(sub_a) == len(sub_b): + dtokens = self._get_dtokens(sub_a, False) + sub_tokens_list.append([dtokens, dtokens]) + else: + sub_tokens_list.append([self._get_dtokens(sub_a, False), self._get_dtokens(sub_b, False)]) + return sub_tokens_list + def _get_config(self): config = OrderedDict( ( diff --git a/spacy/lang/ja/bunsetu.py b/spacy/lang/ja/bunsetu.py deleted file mode 100644 index 7c3eee336..000000000 --- a/spacy/lang/ja/bunsetu.py +++ /dev/null @@ -1,144 +0,0 @@ -# coding: utf8 -from __future__ import unicode_literals - -from .stop_words import STOP_WORDS - - -POS_PHRASE_MAP = { - "NOUN": "NP", - "NUM": "NP", - "PRON": "NP", - "PROPN": "NP", - - "VERB": "VP", - - "ADJ": "ADJP", - - "ADV": "ADVP", - - "CCONJ": "CCONJP", -} - - -# return value: [(bunsetu_tokens, phrase_type={'NP', 'VP', 'ADJP', 'ADVP'}, phrase_tokens)] -def yield_bunsetu(doc, debug=False): - bunsetu = [] - bunsetu_may_end = False - phrase_type = None - phrase = None - prev = None - prev_tag = None - prev_dep = None - prev_head = None - for t in doc: - pos = t.pos_ - pos_type = POS_PHRASE_MAP.get(pos, None) - tag = t.tag_ - dep = t.dep_ - head = t.head.i - if debug: - print(t.i, t.orth_, pos, pos_type, dep, head, bunsetu_may_end, phrase_type, phrase, bunsetu) - - # DET is always an individual bunsetu - if pos == "DET": - if bunsetu: - yield bunsetu, phrase_type, phrase - yield [t], None, None - bunsetu = [] - bunsetu_may_end = False - phrase_type = None - phrase = None - - # PRON or Open PUNCT always splits bunsetu - elif tag == "補助記号-括弧開": - if bunsetu: - yield bunsetu, phrase_type, phrase - bunsetu = [t] - bunsetu_may_end = True - phrase_type = None - phrase = None - - # bunsetu head not appeared - elif phrase_type is None: - if bunsetu and prev_tag == "補助記号-読点": - yield bunsetu, phrase_type, phrase - bunsetu = [] - bunsetu_may_end = False - phrase_type = None - phrase = None - bunsetu.append(t) - if pos_type: # begin phrase - phrase = [t] - phrase_type = pos_type - if pos_type in {"ADVP", "CCONJP"}: - bunsetu_may_end = True - - # entering new bunsetu - elif pos_type and ( - pos_type != phrase_type or # different phrase type arises - bunsetu_may_end # same phrase type but bunsetu already ended - ): - # exceptional case: NOUN to VERB - if phrase_type == "NP" and pos_type == "VP" and prev_dep == 'compound' and prev_head == t.i: - bunsetu.append(t) - phrase_type = "VP" - phrase.append(t) - # exceptional case: VERB to NOUN - elif phrase_type == "VP" and pos_type == "NP" and ( - prev_dep == 'compound' and prev_head == t.i or - dep == 'compound' and prev == head or - prev_dep == 'nmod' and prev_head == t.i - ): - bunsetu.append(t) - phrase_type = "NP" - phrase.append(t) - else: - yield bunsetu, phrase_type, phrase - bunsetu = [t] - bunsetu_may_end = False - phrase_type = pos_type - phrase = [t] - - # NOUN bunsetu - elif phrase_type == "NP": - bunsetu.append(t) - if not bunsetu_may_end and (( - (pos_type == "NP" or pos == "SYM") and (prev_head == t.i or prev_head == head) and prev_dep in {'compound', 'nummod'} - ) or ( - pos == "PART" and (prev == head or prev_head == head) and dep == 'mark' - )): - phrase.append(t) - else: - bunsetu_may_end = True - - # VERB bunsetu - elif phrase_type == "VP": - bunsetu.append(t) - if not bunsetu_may_end and pos == "VERB" and prev_head == t.i and prev_dep == 'compound': - phrase.append(t) - else: - bunsetu_may_end = True - - # ADJ bunsetu - elif phrase_type == "ADJP" and tag != '連体詞': - bunsetu.append(t) - if not bunsetu_may_end and (( - pos == "NOUN" and (prev_head == t.i or prev_head == head) and prev_dep in {'amod', 'compound'} - ) or ( - pos == "PART" and (prev == head or prev_head == head) and dep == 'mark' - )): - phrase.append(t) - else: - bunsetu_may_end = True - - # other bunsetu - else: - bunsetu.append(t) - - prev = t.i - prev_tag = t.tag_ - prev_dep = t.dep_ - prev_head = head - - if bunsetu: - yield bunsetu, phrase_type, phrase diff --git a/spacy/lang/ne/__init__.py b/spacy/lang/ne/__init__.py new file mode 100644 index 000000000..21556277d --- /dev/null +++ b/spacy/lang/ne/__init__.py @@ -0,0 +1,23 @@ +# coding: utf8 +from __future__ import unicode_literals + +from .stop_words import STOP_WORDS +from .lex_attrs import LEX_ATTRS + +from ...language import Language +from ...attrs import LANG + + +class NepaliDefaults(Language.Defaults): + lex_attr_getters = dict(Language.Defaults.lex_attr_getters) + lex_attr_getters.update(LEX_ATTRS) + lex_attr_getters[LANG] = lambda text: "ne" # Nepali language ISO code + stop_words = STOP_WORDS + + +class Nepali(Language): + lang = "ne" + Defaults = NepaliDefaults + + +__all__ = ["Nepali"] diff --git a/spacy/lang/ne/examples.py b/spacy/lang/ne/examples.py new file mode 100644 index 000000000..b3c4f9e73 --- /dev/null +++ b/spacy/lang/ne/examples.py @@ -0,0 +1,22 @@ +# coding: utf8 +from __future__ import unicode_literals + + +""" +Example sentences to test spaCy and its language models. + +>>> from spacy.lang.ne.examples import sentences +>>> docs = nlp.pipe(sentences) +""" + + +sentences = [ + "एप्पलले अमेरिकी स्टार्टअप १ अर्ब डलरमा किन्ने सोच्दै छ", + "स्वायत्त कारहरूले बीमा दायित्व निर्माताहरु तिर बदल्छन्", + "स्यान फ्रांसिस्कोले फुटपाथ वितरण रोबोटहरु प्रतिबंध गर्ने विचार गर्दै छ", + "लन्डन यूनाइटेड किंगडमको एक ठूलो शहर हो।", + "तिमी कहाँ छौ?", + "फ्रान्स को राष्ट्रपति को हो?", + "संयुक्त राज्यको राजधानी के हो?", + "बराक ओबामा कहिले कहिले जन्मेका हुन्?", +] diff --git a/spacy/lang/ne/lex_attrs.py b/spacy/lang/ne/lex_attrs.py new file mode 100644 index 000000000..652307577 --- /dev/null +++ b/spacy/lang/ne/lex_attrs.py @@ -0,0 +1,98 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ..norm_exceptions import BASE_NORMS +from ...attrs import NORM, LIKE_NUM + + +# fmt: off +_stem_suffixes = [ + ["ा", "ि", "ी", "ु", "ू", "ृ", "े", "ै", "ो", "ौ"], + ["ँ", "ं", "्", "ः"], + ["लाई", "ले", "बाट", "को", "मा", "हरू"], + ["हरूलाई", "हरूले", "हरूबाट", "हरूको", "हरूमा"], + ["इलो", "िलो", "नु", "ाउनु", "ई", "इन", "इन्", "इनन्"], + ["एँ", "इँन्", "इस्", "इनस्", "यो", "एन", "यौं", "एनौं", "ए", "एनन्"], + ["छु", "छौँ", "छस्", "छौ", "छ", "छन्", "छेस्", "छे", "छ्यौ", "छिन्", "हुन्छ"], + ["दै", "दिन", "दिँन", "दैनस्", "दैन", "दैनौँ", "दैनौं", "दैनन्"], + ["हुन्न", "न्न", "न्न्स्", "न्नौं", "न्नौ", "न्न्न्", "िई"], + ["अ", "ओ", "ऊ", "अरी", "साथ", "वित्तिकै", "पूर्वक"], + ["याइ", "ाइ", "बार", "वार", "चाँहि"], + ["ने", "ेको", "ेकी", "ेका", "ेर", "दै", "तै", "िकन", "उ", "न", "नन्"] +] +# fmt: on + +# reference 1: https://en.wikipedia.org/wiki/Numbers_in_Nepali_language +# reference 2: https://www.imnepal.com/nepali-numbers/ +_num_words = [ + "शुन्य", + "एक", + "दुई", + "तीन", + "चार", + "पाँच", + "छ", + "सात", + "आठ", + "नौ", + "दश", + "एघार", + "बाह्र", + "तेह्र", + "चौध", + "पन्ध्र", + "सोह्र", + "सोह्र", + "सत्र", + "अठार", + "उन्नाइस", + "बीस", + "तीस", + "चालीस", + "पचास", + "साठी", + "सत्तरी", + "असी", + "नब्बे", + "सय", + "हजार", + "लाख", + "करोड", + "अर्ब", + "खर्ब", +] + + +def norm(string): + # normalise base exceptions, e.g. punctuation or currency symbols + if string in BASE_NORMS: + return BASE_NORMS[string] + # set stem word as norm, if available, adapted from: + # https://github.com/explosion/spaCy/blob/master/spacy/lang/hi/lex_attrs.py + # https://www.researchgate.net/publication/237261579_Structure_of_Nepali_Grammar + for suffix_group in reversed(_stem_suffixes): + length = len(suffix_group[0]) + if len(string) <= length: + break + for suffix in suffix_group: + if string.endswith(suffix): + return string[:-length] + return string + + +def like_num(text): + if text.startswith(("+", "-", "±", "~")): + text = text[1:] + text = text.replace(", ", "").replace(".", "") + if text.isdigit(): + return True + if text.count("/") == 1: + num, denom = text.split("/") + if num.isdigit() and denom.isdigit(): + return True + if text.lower() in _num_words: + return True + return False + + +LEX_ATTRS = {NORM: norm, LIKE_NUM: like_num} diff --git a/spacy/lang/ne/stop_words.py b/spacy/lang/ne/stop_words.py new file mode 100644 index 000000000..f008697d0 --- /dev/null +++ b/spacy/lang/ne/stop_words.py @@ -0,0 +1,498 @@ +# coding: utf8 +from __future__ import unicode_literals + + +# Source: https://github.com/sanjaalcorps/NepaliStopWords/blob/master/NepaliStopWords.txt + +STOP_WORDS = set( + """ +अक्सर +अगाडि +अगाडी +अघि +अझै +अठार +अथवा +अनि +अनुसार +अन्तर्गत +अन्य +अन्यत्र +अन्यथा +अब +अरु +अरुलाई +अरू +अर्को +अर्थात +अर्थात् +अलग +अलि +अवस्था +अहिले +आए +आएका +आएको +आज +आजको +आठ +आत्म +आदि +आदिलाई +आफनो +आफू +आफूलाई +आफै +आफैँ +आफ्नै +आफ्नो +आयो +उ +उक्त +उदाहरण +उनको +उनलाई +उनले +उनि +उनी +उनीहरुको +उन्नाइस +उप +उसको +उसलाई +उसले +उहालाई +ऊ +एउटा +एउटै +एक +एकदम +एघार +ओठ +औ +औं +कता +कति +कतै +कम +कमसेकम +कसरि +कसरी +कसै +कसैको +कसैलाई +कसैले +कसैसँग +कस्तो +कहाँबाट +कहिलेकाहीं +का +काम +कारण +कि +किन +किनभने +कुन +कुनै +कुन्नी +कुरा +कृपया +के +केहि +केही +को +कोहि +कोहिपनि +कोही +कोहीपनि +क्रमशः +गए +गएको +गएर +गयौ +गरि +गरी +गरे +गरेका +गरेको +गरेर +गरौं +गर्छ +गर्छन् +गर्छु +गर्दा +गर्दै +गर्न +गर्नु +गर्नुपर्छ +गर्ने +गैर +घर +चार +चाले +चाहनुहुन्छ +चाहन्छु +चाहिं +चाहिए +चाहिंले +चाहीं +चाहेको +चाहेर +चोटी +चौथो +चौध +छ +छन +छन् +छु +छू +छैन +छैनन् +छौ +छौं +जता +जताततै +जना +जनाको +जनालाई +जनाले +जब +जबकि +जबकी +जसको +जसबाट +जसमा +जसरी +जसलाई +जसले +जस्ता +जस्तै +जस्तो +जस्तोसुकै +जहाँ +जान +जाने +जाहिर +जुन +जुनै +जे +जो +जोपनि +जोपनी +झैं +ठाउँमा +ठीक +ठूलो +त +तता +तत्काल +तथा +तथापि +तथापी +तदनुसार +तपाइ +तपाई +तपाईको +तब +तर +तर्फ +तल +तसरी +तापनि +तापनी +तिन +तिनि +तिनिहरुलाई +तिनी +तिनीहरु +तिनीहरुको +तिनीहरू +तिनीहरूको +तिनै +तिमी +तिर +तिरको +ती +तीन +तुरन्त +तुरुन्त +तुरुन्तै +तेश्रो +तेस्कारण +तेस्रो +तेह्र +तैपनि +तैपनी +त्यत्तिकै +त्यत्तिकैमा +त्यस +त्यसकारण +त्यसको +त्यसले +त्यसैले +त्यसो +त्यस्तै +त्यस्तो +त्यहाँ +त्यहिँ +त्यही +त्यहीँ +त्यहीं +त्यो +त्सपछि +त्सैले +थप +थरि +थरी +थाहा +थिए +थिएँ +थिएन +थियो +दर्ता +दश +दिए +दिएको +दिन +दिनुभएको +दिनुहुन्छ +दुइ +दुइवटा +दुई +देखि +देखिन्छ +देखियो +देखे +देखेको +देखेर +दोश्री +दोश्रो +दोस्रो +द्वारा +धन्न +धेरै +धौ +न +नगर्नु +नगर्नू +नजिकै +नत्र +नत्रभने +नभई +नभएको +नभनेर +नयाँ +नि +निकै +निम्ति +निम्न +निम्नानुसार +निर्दिष्ट +नै +नौ +पक्का +पक्कै +पछाडि +पछाडी +पछि +पछिल्लो +पछी +पटक +पनि +पन्ध्र +पर्छ +पर्थ्यो +पर्दैन +पर्ने +पर्नेमा +पर्याप्त +पहिले +पहिलो +पहिल्यै +पाँच +पांच +पाचौँ +पाँचौं +पिच्छे +पूर्व +पो +प्रति +प्रतेक +प्रत्यक +प्राय +प्लस +फरक +फेरि +फेरी +बढी +बताए +बने +बरु +बाट +बारे +बाहिर +बाहेक +बाह्र +बिच +बिचमा +बिरुद्ध +बिशेष +बिस +बीच +बीचमा +बीस +भए +भएँ +भएका +भएकालाई +भएको +भएन +भएर +भन +भने +भनेको +भनेर +भन् +भन्छन् +भन्छु +भन्दा +भन्दै +भन्नुभयो +भन्ने +भन्या +भयेन +भयो +भर +भरि +भरी +भा +भित्र +भित्री +भीत्र +म +मध्य +मध्ये +मलाई +मा +मात्र +मात्रै +माथि +माथी +मुख्य +मुनि +मुन्तिर +मेरो +मैले +यति +यथोचित +यदि +यद्ध्यपि +यद्यपि +यस +यसका +यसको +यसपछि +यसबाहेक +यसमा +यसरी +यसले +यसो +यस्तै +यस्तो +यहाँ +यहाँसम्म +यही +या +यी +यो +र +रही +रहेका +रहेको +रहेछ +राखे +राख्छ +राम्रो +रुपमा +रूप +रे +लगभग +लगायत +लाई +लाख +लागि +लागेको +ले +वटा +वरीपरी +वा +वाट +वापत +वास्तवमा +शायद +सक्छ +सक्ने +सँग +संग +सँगको +सँगसँगै +सँगै +संगै +सङ्ग +सङ्गको +सट्टा +सत्र +सधै +सबै +सबैको +सबैलाई +समय +समेत +सम्भव +सम्म +सय +सरह +सहित +सहितै +सही +साँच्चै +सात +साथ +साथै +सायद +सारा +सुनेको +सुनेर +सुरु +सुरुको +सुरुमै +सो +सोचेको +सोचेर +सोही +सोह्र +स्थित +स्पष्ट +हजार +हरे +हरेक +हामी +हामीले +हाम्रा +हाम्रो +हुँदैन +हुन +हुनत +हुनु +हुने +हुनेछ +हुन् +हुन्छ +हुन्थ्यो +हैन +हो +होइन +होकि +होला +""".split() +) diff --git a/spacy/lexeme.pyx b/spacy/lexeme.pyx index 1df516dcb..8042098d7 100644 --- a/spacy/lexeme.pyx +++ b/spacy/lexeme.pyx @@ -349,7 +349,7 @@ cdef class Lexeme: @property def is_oov(self): """RETURNS (bool): Whether the lexeme is out-of-vocabulary.""" - return self.orth in self.vocab.vectors + return self.orth not in self.vocab.vectors property is_stop: """RETURNS (bool): Whether the lexeme is a stop word.""" diff --git a/spacy/pipeline/pipes.pyx b/spacy/pipeline/pipes.pyx index 3f40cb545..8f07bf8f7 100644 --- a/spacy/pipeline/pipes.pyx +++ b/spacy/pipeline/pipes.pyx @@ -528,10 +528,10 @@ class Tagger(Pipe): new_tag_map[tag] = orig_tag_map[tag] else: new_tag_map[tag] = {POS: X} - if "_SP" in orig_tag_map: - new_tag_map["_SP"] = orig_tag_map["_SP"] cdef Vocab vocab = self.vocab if new_tag_map: + if "_SP" in orig_tag_map: + new_tag_map["_SP"] = orig_tag_map["_SP"] vocab.morphology = Morphology(vocab.strings, new_tag_map, vocab.morphology.lemmatizer, exc=vocab.morphology.exc) diff --git a/spacy/tests/conftest.py b/spacy/tests/conftest.py index 1f13da5d6..91b7e4d9d 100644 --- a/spacy/tests/conftest.py +++ b/spacy/tests/conftest.py @@ -170,6 +170,11 @@ def nb_tokenizer(): return get_lang_class("nb").Defaults.create_tokenizer() +@pytest.fixture(scope="session") +def ne_tokenizer(): + return get_lang_class("ne").Defaults.create_tokenizer() + + @pytest.fixture(scope="session") def nl_tokenizer(): return get_lang_class("nl").Defaults.create_tokenizer() diff --git a/spacy/tests/lang/ja/test_tokenizer.py b/spacy/tests/lang/ja/test_tokenizer.py index 26be5cf59..651e906eb 100644 --- a/spacy/tests/lang/ja/test_tokenizer.py +++ b/spacy/tests/lang/ja/test_tokenizer.py @@ -4,7 +4,7 @@ from __future__ import unicode_literals import pytest from ...tokenizer.test_naughty_strings import NAUGHTY_STRINGS -from spacy.lang.ja import Japanese +from spacy.lang.ja import Japanese, DetailedToken # fmt: off TOKENIZER_TESTS = [ @@ -96,6 +96,57 @@ def test_ja_tokenizer_split_modes(ja_tokenizer, text, len_a, len_b, len_c): assert len(nlp_c(text)) == len_c +@pytest.mark.parametrize("text,sub_tokens_list_a,sub_tokens_list_b,sub_tokens_list_c", + [ + ( + "選挙管理委員会", + [None, None, None, None], + [None, None, [ + [ + DetailedToken(surface='委員', tag='名詞-普通名詞-一般', inf='', lemma='委員', reading='イイン', sub_tokens=None), + DetailedToken(surface='会', tag='名詞-普通名詞-一般', inf='', lemma='会', reading='カイ', sub_tokens=None), + ] + ]], + [[ + [ + DetailedToken(surface='選挙', tag='名詞-普通名詞-サ変可能', inf='', lemma='選挙', reading='センキョ', sub_tokens=None), + DetailedToken(surface='管理', tag='名詞-普通名詞-サ変可能', inf='', lemma='管理', reading='カンリ', sub_tokens=None), + DetailedToken(surface='委員', tag='名詞-普通名詞-一般', inf='', lemma='委員', reading='イイン', sub_tokens=None), + DetailedToken(surface='会', tag='名詞-普通名詞-一般', inf='', lemma='会', reading='カイ', sub_tokens=None), + ], [ + DetailedToken(surface='選挙', tag='名詞-普通名詞-サ変可能', inf='', lemma='選挙', reading='センキョ', sub_tokens=None), + DetailedToken(surface='管理', tag='名詞-普通名詞-サ変可能', inf='', lemma='管理', reading='カンリ', sub_tokens=None), + DetailedToken(surface='委員会', tag='名詞-普通名詞-一般', inf='', lemma='委員会', reading='イインカイ', sub_tokens=None), + ] + ]] + ), + ] +) +def test_ja_tokenizer_sub_tokens(ja_tokenizer, text, sub_tokens_list_a, sub_tokens_list_b, sub_tokens_list_c): + nlp_a = Japanese(meta={"tokenizer": {"config": {"split_mode": "A"}}}) + nlp_b = Japanese(meta={"tokenizer": {"config": {"split_mode": "B"}}}) + nlp_c = Japanese(meta={"tokenizer": {"config": {"split_mode": "C"}}}) + + assert ja_tokenizer(text).user_data["sub_tokens"] == sub_tokens_list_a + assert nlp_a(text).user_data["sub_tokens"] == sub_tokens_list_a + assert nlp_b(text).user_data["sub_tokens"] == sub_tokens_list_b + assert nlp_c(text).user_data["sub_tokens"] == sub_tokens_list_c + + +@pytest.mark.parametrize("text,inflections,reading_forms", + [ + ( + "取ってつけた", + ("五段-ラ行,連用形-促音便", "", "下一段-カ行,連用形-一般", "助動詞-タ,終止形-一般"), + ("トッ", "テ", "ツケ", "タ"), + ), + ] +) +def test_ja_tokenizer_inflections_reading_forms(ja_tokenizer, text, inflections, reading_forms): + assert ja_tokenizer(text).user_data["inflections"] == inflections + assert ja_tokenizer(text).user_data["reading_forms"] == reading_forms + + def test_ja_tokenizer_emptyish_texts(ja_tokenizer): doc = ja_tokenizer("") assert len(doc) == 0 diff --git a/spacy/tests/lang/ne/__init__.py b/spacy/tests/lang/ne/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/spacy/tests/lang/ne/test_text.py b/spacy/tests/lang/ne/test_text.py new file mode 100644 index 000000000..926a7de04 --- /dev/null +++ b/spacy/tests/lang/ne/test_text.py @@ -0,0 +1,19 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import pytest + + +def test_ne_tokenizer_handlers_long_text(ne_tokenizer): + text = """मैले पाएको सर्टिफिकेटलाई म त बोक्रो सम्झन्छु र अभ्यास तब सुरु भयो, जब मैले कलेज पार गरेँ र जीवनको पढाइ सुरु गरेँ ।""" + tokens = ne_tokenizer(text) + assert len(tokens) == 24 + + +@pytest.mark.parametrize( + "text,length", + [("समय जान कति पनि बेर लाग्दैन ।", 7), ("म ठूलो हुँदै थिएँ ।", 5)], +) +def test_ne_tokenizer_handles_cnts(ne_tokenizer, text, length): + tokens = ne_tokenizer(text) + assert len(tokens) == length \ No newline at end of file diff --git a/spacy/tests/pipeline/test_tagger.py b/spacy/tests/pipeline/test_tagger.py index a5bda9090..1681ffeaa 100644 --- a/spacy/tests/pipeline/test_tagger.py +++ b/spacy/tests/pipeline/test_tagger.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import pytest from spacy.language import Language +from spacy.symbols import POS, NOUN def test_label_types(): @@ -11,3 +12,16 @@ def test_label_types(): nlp.get_pipe("tagger").add_label("A") with pytest.raises(ValueError): nlp.get_pipe("tagger").add_label(9) + + +def test_tagger_begin_training_tag_map(): + """Test that Tagger.begin_training() without gold tuples does not clobber + the tag map.""" + nlp = Language() + tagger = nlp.create_pipe("tagger") + orig_tag_count = len(tagger.labels) + tagger.add_label("A", {"POS": "NOUN"}) + nlp.add_pipe(tagger) + nlp.begin_training() + assert nlp.vocab.morphology.tag_map["A"] == {POS: NOUN} + assert orig_tag_count + 1 == len(nlp.get_pipe("tagger").labels) diff --git a/spacy/tests/vocab_vectors/test_vectors.py b/spacy/tests/vocab_vectors/test_vectors.py index 576ca93d2..b31cef1f2 100644 --- a/spacy/tests/vocab_vectors/test_vectors.py +++ b/spacy/tests/vocab_vectors/test_vectors.py @@ -376,6 +376,6 @@ def test_vector_is_oov(): data[1] = 2.0 vocab.set_vector("cat", data[0]) vocab.set_vector("dog", data[1]) - assert vocab["cat"].is_oov is True - assert vocab["dog"].is_oov is True - assert vocab["hamster"].is_oov is False + assert vocab["cat"].is_oov is False + assert vocab["dog"].is_oov is False + assert vocab["hamster"].is_oov is True diff --git a/spacy/tokens/token.pyx b/spacy/tokens/token.pyx index 45deebc93..8d3406bae 100644 --- a/spacy/tokens/token.pyx +++ b/spacy/tokens/token.pyx @@ -923,7 +923,7 @@ cdef class Token: @property def is_oov(self): """RETURNS (bool): Whether the token is out-of-vocabulary.""" - return self.c.lex.orth in self.vocab.vectors + return self.c.lex.orth not in self.vocab.vectors @property def is_stop(self): diff --git a/spacy/util.py b/spacy/util.py index 5362952e2..923f56b31 100644 --- a/spacy/util.py +++ b/spacy/util.py @@ -208,6 +208,10 @@ def load_model_from_path(model_path, meta=False, **overrides): pipeline = nlp.Defaults.pipe_names elif pipeline in (False, None): pipeline = [] + # skip "vocab" from overrides in component initialization since vocab is + # already configured from overrides when nlp is initialized above + if "vocab" in overrides: + del overrides["vocab"] for name in pipeline: if name not in disable: config = meta.get("pipeline_args", {}).get(name, {}) diff --git a/website/docs/api/goldparse.md b/website/docs/api/goldparse.md index 5df625991..bc33dd4e6 100644 --- a/website/docs/api/goldparse.md +++ b/website/docs/api/goldparse.md @@ -12,18 +12,18 @@ expects true examples of a label to have the value `1.0`, and negative examples of a label to have the value `0.0`. Labels not in the dictionary are treated as missing – the gradient for those labels will be zero. -| Name | Type | Description | -| ----------- | ----------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `doc` | `Doc` | The document the annotations refer to. | -| `words` | iterable | A sequence of unicode word strings. | -| `tags` | iterable | A sequence of strings, representing tag annotations. | -| `heads` | iterable | A sequence of integers, representing syntactic head offsets. | -| `deps` | iterable | A sequence of strings, representing the syntactic relation types. | -| `entities` | iterable | A sequence of named entity annotations, either as BILUO tag strings, or as `(start_char, end_char, label)` tuples, representing the entity positions. If BILUO tag strings, you can specify missing values by setting the tag to None. | -| `cats` | dict | Labels for text classification. Each key in the dictionary is a string label for the category and each value is `1.0` (positive) or `0.0` (negative). | -| `links` | dict | Labels for entity linking. A dict with `(start_char, end_char)` keys, and the values being dicts with `kb_id:value` entries, representing external KB IDs mapped to either `1.0` (positive) or `0.0` (negative). | -| `make_projective` | bool | Whether to projectivize the dependency tree. Defaults to `False.`. | -| **RETURNS** | `GoldParse` | The newly constructed object. | +| Name | Type | Description | +| ----------------- | ----------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `doc` | `Doc` | The document the annotations refer to. | +| `words` | iterable | A sequence of unicode word strings. | +| `tags` | iterable | A sequence of strings, representing tag annotations. | +| `heads` | iterable | A sequence of integers, representing syntactic head offsets. | +| `deps` | iterable | A sequence of strings, representing the syntactic relation types. | +| `entities` | iterable | A sequence of named entity annotations, either as BILUO tag strings, or as `(start_char, end_char, label)` tuples, representing the entity positions. If BILUO tag strings, you can specify missing values by setting the tag to None. | +| `cats` | dict | Labels for text classification. Each key in the dictionary is a string label for the category and each value is `1.0` (positive) or `0.0` (negative). | +| `links` | dict | Labels for entity linking. A dict with `(start_char, end_char)` keys, and the values being dicts with `kb_id:value` entries, representing external KB IDs mapped to either `1.0` (positive) or `0.0` (negative). | +| `make_projective` | bool | Whether to projectivize the dependency tree. Defaults to `False`. | +| **RETURNS** | `GoldParse` | The newly constructed object. | ## GoldParse.\_\_len\_\_ {#len tag="method"} @@ -43,17 +43,17 @@ Whether the provided syntactic annotations form a projective dependency tree. ## Attributes {#attributes} -| Name | Type | Description | -| ------------------------------------ | ---- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `words` | list | The words. | -| `tags` | list | The part-of-speech tag annotations. | -| `heads` | list | The syntactic head annotations. | -| `labels` | list | The syntactic relation-type annotations. | -| `ner` | list | The named entity annotations as BILUO tags. | -| `cand_to_gold` | list | The alignment from candidate tokenization to gold tokenization. | -| `gold_to_cand` | list | The alignment from gold tokenization to candidate tokenization. | -| `cats` 2 | dict | Keys in the dictionary are string category labels with values `1.0` or `0.0`. | -| `links` 2.2 | dict | Keys in the dictionary are `(start_char, end_char)` triples, and the values are dictionaries with `kb_id:value` entries. | +| Name | Type | Description | +| ------------------------------------ | ---- | ------------------------------------------------------------------------------------------------------------------------ | +| `words` | list | The words. | +| `tags` | list | The part-of-speech tag annotations. | +| `heads` | list | The syntactic head annotations. | +| `labels` | list | The syntactic relation-type annotations. | +| `ner` | list | The named entity annotations as BILUO tags. | +| `cand_to_gold` | list | The alignment from candidate tokenization to gold tokenization. | +| `gold_to_cand` | list | The alignment from gold tokenization to candidate tokenization. | +| `cats` 2 | dict | Keys in the dictionary are string category labels with values `1.0` or `0.0`. | +| `links` 2.2 | dict | Keys in the dictionary are `(start_char, end_char)` triples, and the values are dictionaries with `kb_id:value` entries. | ## Utilities {#util} @@ -61,7 +61,8 @@ Whether the provided syntactic annotations form a projective dependency tree. Convert a list of Doc objects into the [JSON-serializable format](/api/annotation#json-input) used by the -[`spacy train`](/api/cli#train) command. Each input doc will be treated as a 'paragraph' in the output doc. +[`spacy train`](/api/cli#train) command. Each input doc will be treated as a +'paragraph' in the output doc. > #### Example > diff --git a/website/docs/api/matcher.md b/website/docs/api/matcher.md index ac2f898e0..7b195e352 100644 --- a/website/docs/api/matcher.md +++ b/website/docs/api/matcher.md @@ -57,7 +57,7 @@ spaCy v2.3, the `Matcher` can also be called on `Span` objects. | Name | Type | Description | | ----------- | ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -| `doclike` | `Doc`/`Span` | The document to match over or a `Span` (as of v2.3).. | +| `doclike` | `Doc`/`Span` | The document to match over or a `Span` (as of v2.3). | | **RETURNS** | list | A list of `(match_id, start, end)` tuples, describing the matches. A match tuple describes a span `doc[start:end`]. The `match_id` is the ID of the added match pattern. | diff --git a/website/docs/usage/101/_pos-deps.md b/website/docs/usage/101/_pos-deps.md index 1a438e424..1e8960edf 100644 --- a/website/docs/usage/101/_pos-deps.md +++ b/website/docs/usage/101/_pos-deps.md @@ -36,7 +36,7 @@ for token in doc: | Text | Lemma | POS | Tag | Dep | Shape | alpha | stop | | ------- | ------- | ------- | ----- | ---------- | ------- | ------- | ------- | | Apple | apple | `PROPN` | `NNP` | `nsubj` | `Xxxxx` | `True` | `False` | -| is | be | `VERB` | `VBZ` | `aux` | `xx` | `True` | `True` | +| is | be | `AUX` | `VBZ` | `aux` | `xx` | `True` | `True` | | looking | look | `VERB` | `VBG` | `ROOT` | `xxxx` | `True` | `False` | | at | at | `ADP` | `IN` | `prep` | `xx` | `True` | `True` | | buying | buy | `VERB` | `VBG` | `pcomp` | `xxxx` | `True` | `False` | diff --git a/website/docs/usage/adding-languages.md b/website/docs/usage/adding-languages.md index d42aad705..29a9a1c27 100644 --- a/website/docs/usage/adding-languages.md +++ b/website/docs/usage/adding-languages.md @@ -662,7 +662,7 @@ One thing to keep in mind is that spaCy expects to train its models from **whole documents**, not just single sentences. If your corpus only contains single sentences, spaCy's models will never learn to expect multi-sentence documents, leading to low performance on real text. To mitigate this problem, you can use -the `-N` argument to the `spacy convert` command, to merge some of the sentences +the `-n` argument to the `spacy convert` command, to merge some of the sentences into longer pseudo-documents. ### Training the tagger and parser {#train-tagger-parser} diff --git a/website/docs/usage/linguistic-features.md b/website/docs/usage/linguistic-features.md index 84bb3d71b..9031a356f 100644 --- a/website/docs/usage/linguistic-features.md +++ b/website/docs/usage/linguistic-features.md @@ -471,7 +471,7 @@ doc = nlp.make_doc("London is a big city in the United Kingdom.") print("Before", doc.ents) # [] header = [ENT_IOB, ENT_TYPE] -attr_array = numpy.zeros((len(doc), len(header))) +attr_array = numpy.zeros((len(doc), len(header)), dtype="uint64") attr_array[0, 0] = 3 # B attr_array[0, 1] = doc.vocab.strings["GPE"] doc.from_array(header, attr_array) @@ -1143,9 +1143,9 @@ from spacy.gold import align other_tokens = ["i", "listened", "to", "obama", "'", "s", "podcasts", "."] spacy_tokens = ["i", "listened", "to", "obama", "'s", "podcasts", "."] cost, a2b, b2a, a2b_multi, b2a_multi = align(other_tokens, spacy_tokens) -print("Misaligned tokens:", cost) # 2 +print("Edit distance:", cost) # 3 print("One-to-one mappings a -> b", a2b) # array([0, 1, 2, 3, -1, -1, 5, 6]) -print("One-to-one mappings b -> a", b2a) # array([0, 1, 2, 3, 5, 6, 7]) +print("One-to-one mappings b -> a", b2a) # array([0, 1, 2, 3, -1, 6, 7]) print("Many-to-one mappings a -> b", a2b_multi) # {4: 4, 5: 4} print("Many-to-one mappings b-> a", b2a_multi) # {} ``` @@ -1153,7 +1153,7 @@ print("Many-to-one mappings b-> a", b2a_multi) # {} Here are some insights from the alignment information generated in the example above: -- Two tokens are misaligned. +- The edit distance (cost) is `3`: two deletions and one insertion. - The one-to-one mappings for the first four tokens are identical, which means they map to each other. This makes sense because they're also identical in the input: `"i"`, `"listened"`, `"to"` and `"obama"`. diff --git a/website/docs/usage/models.md b/website/docs/usage/models.md index 382193157..b11e6347a 100644 --- a/website/docs/usage/models.md +++ b/website/docs/usage/models.md @@ -117,6 +117,18 @@ The Chinese language class supports three word segmentation options: better segmentation for Chinese OntoNotes and the new [Chinese models](/models/zh). + + +Note that [`pkuseg`](https://github.com/lancopku/pkuseg-python) doesn't yet ship +with pre-compiled wheels for Python 3.8. If you're running Python 3.8, you can +install it from our fork and compile it locally: + +```bash +$ pip install https://github.com/honnibal/pkuseg-python/archive/master.zip +``` + + + The `meta` argument of the `Chinese` language class supports the following @@ -196,12 +208,20 @@ nlp = Chinese(meta={"tokenizer": {"config": {"pkuseg_model": "/path/to/pkuseg_mo The Japanese language class uses [SudachiPy](https://github.com/WorksApplications/SudachiPy) for word -segmentation and part-of-speech tagging. The default Japanese language class -and the provided Japanese models use SudachiPy split mode `A`. +segmentation and part-of-speech tagging. The default Japanese language class and +the provided Japanese models use SudachiPy split mode `A`. The `meta` argument of the `Japanese` language class can be used to configure the split mode to `A`, `B` or `C`. + + +If you run into errors related to `sudachipy`, which is currently under active +development, we suggest downgrading to `sudachipy==0.4.5`, which is the version +used for training the current [Japanese models](/models/ja). + + + ## Installing and using models {#download} > #### Downloading models in spaCy < v1.7 diff --git a/website/docs/usage/rule-based-matching.md b/website/docs/usage/rule-based-matching.md index 1db2405d1..f7866fe31 100644 --- a/website/docs/usage/rule-based-matching.md +++ b/website/docs/usage/rule-based-matching.md @@ -1158,17 +1158,17 @@ what you need for your application. > available corpus. For example, the corpus spaCy's [English models](/models/en) were trained on -defines a `PERSON` entity as just the **person name**, without titles like "Mr" -or "Dr". This makes sense, because it makes it easier to resolve the entity type -back to a knowledge base. But what if your application needs the full names, -_including_ the titles? +defines a `PERSON` entity as just the **person name**, without titles like "Mr." +or "Dr.". This makes sense, because it makes it easier to resolve the entity +type back to a knowledge base. But what if your application needs the full +names, _including_ the titles? ```python ### {executable="true"} import spacy nlp = spacy.load("en_core_web_sm") -doc = nlp("Dr Alex Smith chaired first board meeting of Acme Corp Inc.") +doc = nlp("Dr. Alex Smith chaired first board meeting of Acme Corp Inc.") print([(ent.text, ent.label_) for ent in doc.ents]) ``` @@ -1233,7 +1233,7 @@ def expand_person_entities(doc): # Add the component after the named entity recognizer nlp.add_pipe(expand_person_entities, after='ner') -doc = nlp("Dr Alex Smith chaired first board meeting of Acme Corp Inc.") +doc = nlp("Dr. Alex Smith chaired first board meeting of Acme Corp Inc.") print([(ent.text, ent.label_) for ent in doc.ents]) ``` diff --git a/website/docs/usage/v2-3.md b/website/docs/usage/v2-3.md index ba75b01ab..e6b88c779 100644 --- a/website/docs/usage/v2-3.md +++ b/website/docs/usage/v2-3.md @@ -14,10 +14,10 @@ all language models, and decreased model size and loading times for models with vectors. We've added pretrained models for **Chinese, Danish, Japanese, Polish and Romanian** and updated the training data and vectors for most languages. Model packages with vectors are about **2×** smaller on disk and load -**2-4×** faster. For the full changelog, see the [release notes on -GitHub](https://github.com/explosion/spaCy/releases/tag/v2.3.0). For more -details and a behind-the-scenes look at the new release, [see our blog -post](https://explosion.ai/blog/spacy-v2-3). +**2-4×** faster. For the full changelog, see the +[release notes on GitHub](https://github.com/explosion/spaCy/releases/tag/v2.3.0). +For more details and a behind-the-scenes look at the new release, +[see our blog post](https://explosion.ai/blog/spacy-v2-3). ### Expanded model families with vectors {#models} @@ -33,10 +33,10 @@ post](https://explosion.ai/blog/spacy-v2-3). With new model families for Chinese, Danish, Polish, Romanian and Chinese plus `md` and `lg` models with word vectors for all languages, this release provides -a total of 46 model packages. For models trained using [Universal -Dependencies](https://universaldependencies.org) corpora, the training data has -been updated to UD v2.5 (v2.6 for Japanese, v2.3 for Polish) and Dutch has been -extended to include both UD Dutch Alpino and LassySmall. +a total of 46 model packages. For models trained using +[Universal Dependencies](https://universaldependencies.org) corpora, the +training data has been updated to UD v2.5 (v2.6 for Japanese, v2.3 for Polish) +and Dutch has been extended to include both UD Dutch Alpino and LassySmall. @@ -48,6 +48,7 @@ extended to include both UD Dutch Alpino and LassySmall. ### Chinese {#chinese} > #### Example +> > ```python > from spacy.lang.zh import Chinese > @@ -57,41 +58,49 @@ extended to include both UD Dutch Alpino and LassySmall. > > # Append words to user dict > nlp.tokenizer.pkuseg_update_user_dict(["中国", "ABC"]) +> ``` This release adds support for -[pkuseg](https://github.com/lancopku/pkuseg-python) for word segmentation and -the new Chinese models ship with a custom pkuseg model trained on OntoNotes. -The Chinese tokenizer can be initialized with both `pkuseg` and custom models -and the `pkuseg` user dictionary is easy to customize. +[`pkuseg`](https://github.com/lancopku/pkuseg-python) for word segmentation and +the new Chinese models ship with a custom pkuseg model trained on OntoNotes. The +Chinese tokenizer can be initialized with both `pkuseg` and custom models and +the `pkuseg` user dictionary is easy to customize. Note that +[`pkuseg`](https://github.com/lancopku/pkuseg-python) doesn't yet ship with +pre-compiled wheels for Python 3.8. See the +[usage documentation](/usage/models#chinese) for details on how to install it on +Python 3.8. -**Chinese:** [Chinese tokenizer usage](/usage/models#chinese) +**Models:** [Chinese models](/models/zh) **Usage: ** +[Chinese tokenizer usage](/usage/models#chinese) ### Japanese {#japanese} The updated Japanese language class switches to -[SudachiPy](https://github.com/WorksApplications/SudachiPy) for word -segmentation and part-of-speech tagging. Using `sudachipy` greatly simplifies +[`SudachiPy`](https://github.com/WorksApplications/SudachiPy) for word +segmentation and part-of-speech tagging. Using `SudachiPy` greatly simplifies installing spaCy for Japanese, which is now possible with a single command: `pip install spacy[ja]`. -**Japanese:** [Japanese tokenizer usage](/usage/models#japanese) +**Models:** [Japanese models](/models/ja) **Usage:** +[Japanese tokenizer usage](/usage/models#japanese) ### Small CLI updates -- `spacy debug-data` provides the coverage of the vectors in a base model with - `spacy debug-data lang train dev -b base_model` -- `spacy evaluate` supports `blank:lg` (e.g. `spacy evaluate blank:en - dev.json`) to evaluate the tokenization accuracy without loading a model -- `spacy train` on GPU restricts the CPU timing evaluation to the first - iteration +- [`spacy debug-data`](/api/cli#debug-data) provides the coverage of the vectors + in a base model with `spacy debug-data lang train dev -b base_model` +- [`spacy evaluate`](/api/cli#evaluate) supports `blank:lg` (e.g. + `spacy evaluate blank:en dev.json`) to evaluate the tokenization accuracy + without loading a model +- [`spacy train`](/api/cli#train) on GPU restricts the CPU timing evaluation to + the first iteration ## Backwards incompatibilities {#incompat} @@ -100,8 +109,8 @@ installing spaCy for Japanese, which is now possible with a single command: If you've been training **your own models**, you'll need to **retrain** them with the new version. Also don't forget to upgrade all models to the latest versions. Models for earlier v2 releases (v2.0, v2.1, v2.2) aren't compatible -with models for v2.3. To check if all of your models are up to date, you can -run the [`spacy validate`](/api/cli#validate) command. +with models for v2.3. To check if all of your models are up to date, you can run +the [`spacy validate`](/api/cli#validate) command. @@ -116,21 +125,20 @@ run the [`spacy validate`](/api/cli#validate) command. > directly. - If you're training new models, you'll want to install the package - [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data), - which now includes both the lemmatization tables (as in v2.2) and the - normalization tables (new in v2.3). If you're using pretrained models, - **nothing changes**, because the relevant tables are included in the model - packages. + [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data), which + now includes both the lemmatization tables (as in v2.2) and the normalization + tables (new in v2.3). If you're using pretrained models, **nothing changes**, + because the relevant tables are included in the model packages. - Due to the updated Universal Dependencies training data, the fine-grained part-of-speech tags will change for many provided language models. The coarse-grained part-of-speech tagset remains the same, but the mapping from particular fine-grained to coarse-grained tags may show minor differences. - For French, Italian, Portuguese and Spanish, the fine-grained part-of-speech - tagsets contain new merged tags related to contracted forms, such as - `ADP_DET` for French `"au"`, which maps to UPOS `ADP` based on the head - `"à"`. This increases the accuracy of the models by improving the alignment - between spaCy's tokenization and Universal Dependencies multi-word tokens - used for contractions. + tagsets contain new merged tags related to contracted forms, such as `ADP_DET` + for French `"au"`, which maps to UPOS `ADP` based on the head `"à"`. This + increases the accuracy of the models by improving the alignment between + spaCy's tokenization and Universal Dependencies multi-word tokens used for + contractions. ### Migrating from spaCy 2.2 {#migrating} @@ -143,29 +151,81 @@ v2.3 so that `token_match` has priority over prefixes and suffixes as in v2.2.1 and earlier versions. A new tokenizer setting `url_match` has been introduced in v2.3.0 to handle -cases like URLs where the tokenizer should remove prefixes and suffixes (e.g., -a comma at the end of a URL) before applying the match. See the full [tokenizer -documentation](/usage/linguistic-features#tokenization) and try out +cases like URLs where the tokenizer should remove prefixes and suffixes (e.g., a +comma at the end of a URL) before applying the match. See the full +[tokenizer documentation](/usage/linguistic-features#tokenization) and try out [`nlp.tokenizer.explain()`](/usage/linguistic-features#tokenizer-debug) when debugging your tokenizer configuration. #### Warnings configuration -spaCy's custom warnings have been replaced with native python +spaCy's custom warnings have been replaced with native Python [`warnings`](https://docs.python.org/3/library/warnings.html). Instead of -setting `SPACY_WARNING_IGNORE`, use the [warnings +setting `SPACY_WARNING_IGNORE`, use the [`warnings` filters](https://docs.python.org/3/library/warnings.html#the-warnings-filter) to manage warnings. +```diff +import spacy ++ import warnings + +- spacy.errors.SPACY_WARNING_IGNORE.append('W007') ++ warnings.filterwarnings("ignore", message=r"\\[W007\\]", category=UserWarning) +``` + #### Normalization tables The normalization tables have moved from the language data in -[`spacy/lang`](https://github.com/explosion/spaCy/tree/master/spacy/lang) to -the package -[`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data). If -you're adding data for a new language, the normalization table should be added -to `spacy-lookups-data`. See [adding norm -exceptions](/usage/adding-languages#norm-exceptions). +[`spacy/lang`](https://github.com/explosion/spaCy/tree/master/spacy/lang) to the +package [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data). +If you're adding data for a new language, the normalization table should be +added to `spacy-lookups-data`. See +[adding norm exceptions](/usage/adding-languages#norm-exceptions). + +#### No preloaded lexemes/vocab for models with vectors + +To reduce the initial loading time, the lexemes in `nlp.vocab` are no longer +loaded on initialization for models with vectors. As you process texts, the +lexemes will be added to the vocab automatically, just as in models without +vectors. + +To see the number of unique vectors and number of words with vectors, see +`nlp.meta['vectors']`, for example for `en_core_web_md` there are `20000` +unique vectors and `684830` words with vectors: + +```python +{ + 'width': 300, + 'vectors': 20000, + 'keys': 684830, + 'name': 'en_core_web_md.vectors' +} +``` + +If required, for instance if you are working directly with word vectors rather +than processing texts, you can load all lexemes for words with vectors at once: + +```python +for orth in nlp.vocab.vectors: + _ = nlp.vocab[orth] +``` + +#### Lexeme.is_oov and Token.is_oov + + + +Due to a bug, the values for `is_oov` are reversed in v2.3.0, but this will be +fixed in the next patch release v2.3.1. + + + +In v2.3, `Lexeme.is_oov` and `Token.is_oov` are `True` if the lexeme does not +have a word vector. This is equivalent to `token.orth not in +nlp.vocab.vectors`. + +Previously in v2.2, `is_oov` corresponded to whether a lexeme had stored +probability and cluster features. The probability and cluster features are no +longer included in the provided medium and large models (see the next section). #### Probability and cluster features @@ -181,28 +241,28 @@ exceptions](/usage/adding-languages#norm-exceptions). The `Token.prob` and `Token.cluster` features, which are no longer used by the core pipeline components as of spaCy v2, are no longer provided in the -pretrained models to reduce the model size. To keep these features available -for users relying on them, the `prob` and `cluster` features for the most -frequent 1M tokens have been moved to +pretrained models to reduce the model size. To keep these features available for +users relying on them, the `prob` and `cluster` features for the most frequent +1M tokens have been moved to [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data) as `extra` features for the relevant languages (English, German, Greek and Spanish). The extra tables are loaded lazily, so if you have `spacy-lookups-data` -installed and your code accesses `Token.prob`, the full table is loaded into -the model vocab, which will take a few seconds on initial loading. When you -save this model after loading the `prob` table, the full `prob` table will be -saved as part of the model vocab. +installed and your code accesses `Token.prob`, the full table is loaded into the +model vocab, which will take a few seconds on initial loading. When you save +this model after loading the `prob` table, the full `prob` table will be saved +as part of the model vocab. -If you'd like to include custom `cluster`, `prob`, or `sentiment` tables as -part of a new model, add the data to +If you'd like to include custom `cluster`, `prob`, or `sentiment` tables as part +of a new model, add the data to [`spacy-lookups-data`](https://github.com/explosion/spacy-lookups-data) under the entry point `lg_extra`, e.g. `en_extra` for English. Alternatively, you can initialize your [`Vocab`](/api/vocab) with the `lookups_extra` argument with a [`Lookups`](/api/lookups) object that includes the tables `lexeme_cluster`, `lexeme_prob`, `lexeme_sentiment` or `lexeme_settings`. `lexeme_settings` is -currently only used to provide a custom `oov_prob`. See examples in the [`data` -directory](https://github.com/explosion/spacy-lookups-data/tree/master/spacy_lookups_data/data) +currently only used to provide a custom `oov_prob`. See examples in the +[`data` directory](https://github.com/explosion/spacy-lookups-data/tree/master/spacy_lookups_data/data) in `spacy-lookups-data`. #### Initializing new models without extra lookups tables diff --git a/website/meta/site.json b/website/meta/site.json index 29d71048e..8b8424f82 100644 --- a/website/meta/site.json +++ b/website/meta/site.json @@ -23,9 +23,9 @@ "apiKey": "371e26ed49d29a27bd36273dfdaf89af", "indexName": "spacy" }, - "binderUrl": "ines/spacy-io-binder", + "binderUrl": "explosion/spacy-io-binder", "binderBranch": "live", - "binderVersion": "2.2.0", + "binderVersion": "2.3.0", "sections": [ { "id": "usage", "title": "Usage Documentation", "theme": "blue" }, { "id": "models", "title": "Models Documentation", "theme": "blue" },