diff --git a/.github/contributors/munozbravo.md b/.github/contributors/munozbravo.md new file mode 100644 index 000000000..b36133e1e --- /dev/null +++ b/.github/contributors/munozbravo.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 | Germán Muñoz | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2019-06-01 | +| GitHub username | munozbravo | +| Website (optional) | | diff --git a/spacy/lang/es/__init__.py b/spacy/lang/es/__init__.py index d5d6e4f23..d49948b30 100644 --- a/spacy/lang/es/__init__.py +++ b/spacy/lang/es/__init__.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from .tag_map import TAG_MAP from .stop_words import STOP_WORDS +from .lex_attrs import LEX_ATTRS from .lemmatizer import LOOKUP from .syntax_iterators import SYNTAX_ITERATORS @@ -16,6 +17,7 @@ from ...util import update_exc, add_lookups class SpanishDefaults(Language.Defaults): lex_attr_getters = dict(Language.Defaults.lex_attr_getters) + lex_attr_getters.update(LEX_ATTRS) lex_attr_getters[LANG] = lambda text: "es" lex_attr_getters[NORM] = add_lookups( Language.Defaults.lex_attr_getters[NORM], BASE_NORMS diff --git a/spacy/lang/es/lex_attrs.py b/spacy/lang/es/lex_attrs.py new file mode 100644 index 000000000..03ada1f43 --- /dev/null +++ b/spacy/lang/es/lex_attrs.py @@ -0,0 +1,59 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ...attrs import LIKE_NUM + + +_num_words = [ + "cero", + "uno", + "dos", + "tres", + "cuatro", + "cinco", + "seis", + "siete", + "ocho", + "nueve", + "diez", + "once", + "doce", + "trece", + "catorce", + "quince", + "dieciséis", + "diecisiete", + "dieciocho", + "diecinueve", + "veinte", + "treinta", + "cuarenta", + "cincuenta", + "sesenta", + "setenta", + "ochenta", + "noventa", + "cien", + "mil", + "millón", + "billón", + "trillón", +] + + +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 = {LIKE_NUM: like_num} diff --git a/spacy/tests/regression/test_issue3803.py b/spacy/tests/regression/test_issue3803.py new file mode 100644 index 000000000..4d9b664fa --- /dev/null +++ b/spacy/tests/regression/test_issue3803.py @@ -0,0 +1,15 @@ +# coding: utf8 +from __future__ import unicode_literals + +import pytest + +from spacy.lang.es import Spanish + + +def test_issue3803(): + """Test that spanish num-like tokens have True for like_num attribute.""" + nlp = Spanish() + text = "2 dos 1000 mil 12 doce" + doc = nlp(text) + + assert [t.like_num for t in doc] == [True, True, True, True, True, True] diff --git a/website/meta/universe.json b/website/meta/universe.json index 39602e0bb..5155493bd 100644 --- a/website/meta/universe.json +++ b/website/meta/universe.json @@ -1,22 +1,107 @@ { "resources": [ + { + "id": "nlp-architect", + "title": "NLP Architect", + "slogan": "Python lib for exploring Deep NLP & NLU by Intel AI", + "github": "NervanaSystems/nlp-architect", + "pip": "nlp-architect", + "thumb": "https://i.imgur.com/vMideRx.png", + "category": ["standalone", "research"], + "tags": ["pytorch"] + }, + { + "id": "NeuroNER", + "title": "NeuroNER", + "slogan": "Named-entity recognition using neural networks", + "github": "Franck-Dernoncourt/NeuroNER", + "pip": "pyneuroner[cpu]", + "code_example": [ + "from neuroner import neuromodel", + "nn = neuromodel.NeuroNER(train_model=False, use_pretrained_model=True)" + ], + "category": ["ner"], + "tags": ["standalone"] + }, + { + "id": "NLPre", + "title": "NLPre", + "slogan": "Natural Language Preprocessing Library for health data and more", + "github": "NIHOPA/NLPre", + "pip": "nlpre", + "code_example": [ + "from nlpre import titlecaps, dedash, identify_parenthetical_phrases", + "from nlpre import replace_acronyms, replace_from_dictionary", + "ABBR = identify_parenthetical_phrases()(text)", + "parsers = [dedash(), titlecaps(), replace_acronyms(ABBR),", + " replace_from_dictionary(prefix='MeSH_')]", + "for f in parsers:", + " text = f(text)", + "print(text)" + ], + "category": ["scientific"] + }, + { + "id": "Chatterbot", + "title": "Chatterbot", + "slogan": "A machine-learning based conversational dialog engine for creating chat bots", + "github": "gunthercox/ChatterBot", + "pip": "chatterbot", + "thumb": "https://i.imgur.com/eyAhwXk.jpg", + "code_example": [ + "from chatterbot import ChatBot", + "from chatterbot.trainers import ListTrainer", + "# Create a new chat bot named Charlie", + "chatbot = ChatBot('Charlie')", + "trainer = ListTrainer(chatbot)", + "trainer.train([", + "'Hi, can I help you?',", + "'Sure, I would like to book a flight to Iceland.", + "'Your flight has been booked.'", + "])", + "", + "response = chatbot.get_response('I would like to book a flight.')" + ], + "author": "Gunther Cox", + "author_links": { + "github": "gunthercox" + }, + "category": ["conversational", "standalone"], + "tags": ["chatbots"] + }, { "id": "saber", "title": "saber", - "slogan": "deep-learning based tool for information extraction in the biomedical domain", + "slogan": "Deep-learning based tool for information extraction in the biomedical domain", "github": "BaderLab/saber", "pip": "saber", "thumb": "https://raw.githubusercontent.com/BaderLab/saber/master/docs/img/saber_logo.png", "code_example": [ - ">>> from saber.saber import Saber", - ">>> saber = Saber()", - ">>> saber.load('PRGE')", + "from saber.saber import Saber", + "saber = Saber()", + "saber.load('PRGE')", "saber.annotate('The phosphorylation of Hdm2 by MK2 promotes the ubiquitination of p53.')" ], - "category": ["research", "biomedical"], - "tags": ["keras"] + "author": "Bader Lab, University of Toronto", + "category": ["scientific"], + "tags": ["keras", "biomedical"] + }, + { + "id": "alibi", + "title": "alibi", + "slogan": "Algorithms for monitoring and explaining machine learning models ", + "github": "SeldonIO/alibi", + "pip": "alibi", + "thumb": "https://i.imgur.com/YkzQHRp.png", + "code_example": [ + "from alibi.explainers import AnchorTabular", + "explainer = AnchorTabular(predict_fn, feature_names)", + "explainer.fit(X_train)", + "explainer.explain(x)" + ], + "author": "Seldon", + "category": ["standalone", "research"] }, - { "id": "spacymoji", "slogan": "Emoji handling and meta data as a spaCy pipeline component", @@ -160,7 +245,7 @@ "doc = nlp(my_doc_text)" ], "author": "tc64", - "author_link": { + "author_links": { "github": "tc64" }, "category": ["pipeline"] @@ -363,7 +448,7 @@ "author_links": { "github": "huggingface" }, - "category": ["standalone", "conversational"], + "category": ["standalone", "conversational", "models"], "tags": ["coref"] }, { @@ -555,7 +640,7 @@ "twitter": "allenai_org", "website": "http://allenai.org" }, - "category": ["models", "research"] + "category": ["scientific", "models", "research"] }, { "id": "textacy", @@ -618,7 +703,7 @@ "github": "ahalterman", "twitter": "ahalterman" }, - "category": ["standalone"] + "category": ["standalone", "scientific"] }, { "id": "kindred", @@ -643,7 +728,7 @@ "author_links": { "github": "jakelever" }, - "category": ["standalone"] + "category": ["standalone", "scientific"] }, { "id": "sense2vec", @@ -911,6 +996,23 @@ "author": "Aaron Kramer", "category": ["courses"] }, + { + "type": "education", + "id": "spacy-course", + "title": "Advanced NLP with spaCy", + "slogan": "spaCy, 2019", + "description": "In this free interactive course, you'll learn how to use spaCy to build advanced natural language understanding systems, using both rule-based and machine learning approaches.", + "url": "https://course.spacy.io", + "image": "https://i.imgur.com/JC00pHW.jpg", + "thumb": "https://i.imgur.com/5RXLtrr.jpg", + "author": "Ines Montani", + "author_links": { + "twitter": "_inesmontani", + "github": "ines", + "website": "https://ines.io" + }, + "category": ["courses"] + }, { "type": "education", "id": "video-spacys-ner-model", @@ -1071,7 +1173,7 @@ "github": "ecohealthalliance", "website": " https://ecohealthalliance.org/" }, - "category": ["research", "standalone"] + "category": ["scientific", "standalone"] }, { "id": "self-attentive-parser", @@ -1393,7 +1495,7 @@ "url": "https://github.com/msg-systems/holmes-extractor", "description": "Holmes is a Python 3 library that supports a number of use cases involving information extraction from English and German texts, including chatbot, structural search, topic matching and supervised document classification.", "pip": "holmes-extractor", - "category": ["conversational", "research", "standalone"], + "category": ["conversational", "standalone"], "tags": ["chatbots", "text-processing"], "code_example": [ "import holmes_extractor as holmes", @@ -1432,6 +1534,11 @@ "title": "Research", "description": "Frameworks and utilities for developing better NLP models, especially using neural networks" }, + { + "id": "scientific", + "title": "Scientific", + "description": "Frameworks and utilities for scientific text processing" + }, { "id": "visualizers", "title": "Visualizers", @@ -1451,6 +1558,11 @@ "id": "standalone", "title": "Standalone", "description": "Self-contained libraries or tools that use spaCy under the hood" + }, + { + "id": "models", + "title": "Models", + "description": "Third-party pre-trained models for different languages and domains" } ] },