From c7d53348d7c0474852dc5ebe5794f2816ef7eb01 Mon Sep 17 00:00:00 2001 From: Maciej <32799095+mpszumowski@users.noreply.github.com> Date: Wed, 30 May 2018 12:28:44 +0200 Subject: [PATCH] Fix bug in CLI iob and ner converter (#2392) (fixes #2385) * issue_2385 add tests for iob_to_biluo converter function * issue_2385 fix and modify iob_to_biluo function to accept either iob or biluo tags in cli.converter * issue_2385 add test to fix b char bug * add contributor agreement * fill contributor agreement --- .github/contributors/mpszumowski.md | 106 +++++++++++++++++++++++ spacy/gold.pyx | 8 +- spacy/tests/regression/test_issue2385.py | 34 ++++++++ 3 files changed, 145 insertions(+), 3 deletions(-) create mode 100644 .github/contributors/mpszumowski.md create mode 100644 spacy/tests/regression/test_issue2385.py diff --git a/.github/contributors/mpszumowski.md b/.github/contributors/mpszumowski.md new file mode 100644 index 000000000..226c400c6 --- /dev/null +++ b/.github/contributors/mpszumowski.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 UG (haftungsbeschränkt)](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 | Maciej Szumowski | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 30.05.2018 | +| GitHub username | mpszumowski | +| Website (optional) | | diff --git a/spacy/gold.pyx b/spacy/gold.pyx index 49ee9083d..e396aa7c6 100644 --- a/spacy/gold.pyx +++ b/spacy/gold.pyx @@ -353,12 +353,14 @@ def _consume_os(tags): def _consume_ent(tags): if not tags: return [] - target = tags.pop(0).replace('B', 'I') + tag = tags.pop(0) + target_in = 'I' + tag[1:] + target_last = 'L' + tag[1:] length = 1 - while tags and tags[0] == target: + while tags and tags[0] in {target_in, target_last}: length += 1 tags.pop(0) - label = target[2:] + label = tag[2:] if length == 1: return ['U-' + label] else: diff --git a/spacy/tests/regression/test_issue2385.py b/spacy/tests/regression/test_issue2385.py new file mode 100644 index 000000000..b3e4ba11a --- /dev/null +++ b/spacy/tests/regression/test_issue2385.py @@ -0,0 +1,34 @@ +# coding: utf-8 +import pytest + +from ...gold import iob_to_biluo + + +@pytest.mark.xfail +@pytest.mark.parametrize('tags', [('B-ORG', 'L-ORG'), + ('B-PERSON', 'I-PERSON', 'L-PERSON'), + ('U-BRAWLER', 'U-BRAWLER')]) +def test_issue2385_biluo(tags): + """already biluo format""" + assert iob_to_biluo(tags) == list(tags) + + +@pytest.mark.xfail +@pytest.mark.parametrize('tags', [('B-BRAWLER', 'I-BRAWLER', 'I-BRAWLER')]) +def test_issue2385_iob_bcharacter(tags): + """fix bug in labels with a 'b' character""" + assert iob_to_biluo(tags) == ['B-BRAWLER', 'I-BRAWLER', 'L-BRAWLER'] + + +@pytest.mark.xfail +@pytest.mark.parametrize('tags', [('I-ORG', 'I-ORG', 'B-ORG')]) +def test_issue2385_iob1(tags): + """maintain support for iob1 format""" + assert iob_to_biluo(tags) == ['B-ORG', 'L-ORG', 'U-ORG'] + + +@pytest.mark.xfail +@pytest.mark.parametrize('tags', [('B-PERSON', 'I-PERSON', 'B-PERSON')]) +def test_issue2385_iob2(tags): + """maintain support for iob2 format""" + assert iob_to_biluo(tags) == ['B-PERSON', 'L-PERSON', 'U-PERSON']