From debfb46088ee7eb53a02f80f0d5fa0ea7a8ee5bf Mon Sep 17 00:00:00 2001 From: Pierre Lison Date: Thu, 22 Apr 2021 00:58:09 +0200 Subject: [PATCH 1/2] adding skweak to the SpaCy universe --- website/meta/universe.json | 55 +++++++++++++++++++++++++++++++++++++- 1 file changed, 54 insertions(+), 1 deletion(-) diff --git a/website/meta/universe.json b/website/meta/universe.json index 01aa058b5..7b13e9ac2 100644 --- a/website/meta/universe.json +++ b/website/meta/universe.json @@ -1,5 +1,58 @@ { "resources": [ + { + "id": "skweak", + "title": "skweak", + "slogan": "Weak supervision for NLP", + "description": "`skweak` brings the power of weak supervision to NLP tasks, and in particular sequence labelling and text classification. Instead of annotating documents by hand, `skweak` allows you to define *labelling functions* to automatically label your documents, and then aggregate their results using a statistical model that estimates the accuracy and confusions of each labelling function.", + "github": "https://github.com/NorskRegnesentral/skweak", + "pip": "skweak", + "code_example": [ + "import spacy, re", + "from skweak import heuristics, gazetteers, aggregation, utils", + "", + "# LF 1: heuristic to detect occurrences of MONEY entities", + "def money_detector(doc):", + " for tok in doc[1:]:", + " if tok.text[0].isdigit() and tok.nbor(-1).is_currency:", + " yield tok.i-1, tok.i+1, 'MONEY'", + "lf1 = heuristics.FunctionAnnotator('money', money_detector)", + "", + "# LF 2: detection of years with a regex", + "lf2= heuristics.TokenConstraintAnnotator ('years', lambda tok: re.match('(19|20)\\d{2}$', tok.text), 'DATE')", + "", + "# LF 3: a gazetteer with a few names", + "NAMES = [('Barack', 'Obama'), ('Donald', 'Trump'), ('Joe', 'Biden')]", + "trie = gazetteers.Trie(NAMES)", + "lf3 = gazetteers.GazetteerAnnotator('presidents', {'PERSON':trie})", + "", + "# We create a corpus (here with a single text)", + "nlp = spacy.load('en_core_web_sm')", + "doc = nlp('Donald Trump paid $750 in federal income taxes in 2016')", + "", + "# apply the labelling functions", + "doc = lf3(lf2(lf1(doc)))", + "", + "# and aggregate them", + "hmm = aggregation.HMM('hmm', ['PERSON', 'DATE', 'MONEY'])", + "hmm.fit_and_aggregate([doc])", + "", + "# we can then visualise the final result (in Jupyter)", + "utils.display_entities(doc, 'hmm')" + ], + "code_language": "python", + "url": "https://github.com/NorskRegnesentral/skweak", + "thumb": "https://raw.githubusercontent.com/NorskRegnesentral/skweak/main/data/skweak_logo_thumbnail.jpg", + "image": "https://raw.githubusercontent.com/NorskRegnesentral/skweak/main/data/skweak_logo.jpg", + "author": "Pierre Lison", + "author_links": { + "twitter": "plison2", + "github": "plison", + "website": "https://www.nr.no/~plison" + }, + "category": ["pipeline", "standalone", "research", "training"], + "tags": [] + }, { "id": "numerizer", "title": "numerizer", @@ -3002,4 +3055,4 @@ ] } ] -} +} \ No newline at end of file From 2f0ef2c9ccb6aa584f00b5213f44bf089f7ba9ff Mon Sep 17 00:00:00 2001 From: Pierre Lison Date: Thu, 22 Apr 2021 01:16:34 +0200 Subject: [PATCH 2/2] adding skweak to the SpaCy universe --- .github/contributors/plison.md | 106 +++++++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/plison.md diff --git a/.github/contributors/plison.md b/.github/contributors/plison.md new file mode 100644 index 000000000..e98b096b4 --- /dev/null +++ b/.github/contributors/plison.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: + + * [ ] 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 | Pierre Lison | +| Company name (if applicable) | Norsk Regnesentral | +| Title or role (if applicable) | Senior Researcher | +| Date | 22.04.2021 | +| GitHub username | plison | +| Website (optional) | www.nr.no/~plison |