From eea7d4f4a8b4e154ca6897f5dd01e57e97476e50 Mon Sep 17 00:00:00 2001 From: Ziming He Date: Thu, 15 Aug 2019 12:13:32 -0400 Subject: [PATCH] biluo_tags_from_offsets throw exception for overlapping entities (#4021) * Check whether two entities overlap - biluo_gold_biluo_overlap now throw exception when entities passed in have overlaps - added unit test * SCA agreement --- .github/contributors/ryanzhe.md | 106 ++++++++++++++++++++++++++++++++ spacy/gold.pyx | 12 ++++ spacy/tests/test_gold.py | 10 ++- 3 files changed, 127 insertions(+), 1 deletion(-) create mode 100644 .github/contributors/ryanzhe.md diff --git a/.github/contributors/ryanzhe.md b/.github/contributors/ryanzhe.md new file mode 100644 index 000000000..afb250a4c --- /dev/null +++ b/.github/contributors/ryanzhe.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: + + * [ ] 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 my + contributions. + + * [x] 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 | Ziming He | +| Company name (if applicable) | Georgia Tech | +| Title or role (if applicable) | Student | +| Date | 2019-07-24 | +| GitHub username | RyanZHe | +| Website (optional) | www.papermachine.me | diff --git a/spacy/gold.pyx b/spacy/gold.pyx index dab65f48e..64c2d9772 100644 --- a/spacy/gold.pyx +++ b/spacy/gold.pyx @@ -678,11 +678,23 @@ def biluo_tags_from_offsets(doc, entities, missing="O"): >>> tags = biluo_tags_from_offsets(doc, entities) >>> assert tags == ["O", "O", 'U-LOC', "O"] """ + # Ensure no overlapping entity labels exist + tokens_in_ents = {} + starts = {token.idx: token.i for token in doc} ends = {token.idx + len(token): token.i for token in doc} biluo = ["-" for _ in doc] # Handle entity cases for start_char, end_char, label in entities: + for token_index in range(start_char, end_char): + if token_index in tokens_in_ents.keys(): + raise ValueError(Errors.E103.format( + span1=(tokens_in_ents[token_index][0], + tokens_in_ents[token_index][1], + tokens_in_ents[token_index][2]), + span2=(start_char, end_char, label))) + tokens_in_ents[token_index] = (start_char, end_char, label) + start_token = starts.get(start_char) end_token = ends.get(end_char) # Only interested if the tokenization is correct diff --git a/spacy/tests/test_gold.py b/spacy/tests/test_gold.py index d370eac53..ac08716b7 100644 --- a/spacy/tests/test_gold.py +++ b/spacy/tests/test_gold.py @@ -4,7 +4,7 @@ from __future__ import unicode_literals from spacy.gold import biluo_tags_from_offsets, offsets_from_biluo_tags from spacy.gold import spans_from_biluo_tags, GoldParse from spacy.tokens import Doc - +import pytest def test_gold_biluo_U(en_vocab): words = ["I", "flew", "to", "London", "."] @@ -32,6 +32,14 @@ def test_gold_biluo_BIL(en_vocab): tags = biluo_tags_from_offsets(doc, entities) assert tags == ["O", "O", "O", "B-LOC", "I-LOC", "L-LOC", "O"] +def test_gold_biluo_overlap(en_vocab): + words = ["I", "flew", "to", "San", "Francisco", "Valley", "."] + spaces = [True, True, True, True, True, False, True] + doc = Doc(en_vocab, words=words, spaces=spaces) + entities = [(len("I flew to "), len("I flew to San Francisco Valley"), "LOC"), + (len("I flew to "), len("I flew to San Francisco"), "LOC")] + with pytest.raises(ValueError): + tags = biluo_tags_from_offsets(doc, entities) def test_gold_biluo_misalign(en_vocab): words = ["I", "flew", "to", "San", "Francisco", "Valley."]