From 050e2445a882789a3d162cfc3fe6262a7ce1d98d Mon Sep 17 00:00:00 2001 From: gustavengstrom Date: Mon, 21 Oct 2019 12:57:06 +0200 Subject: [PATCH] Adding noun_chunks to the Swedish language model (sv) (#4422) * Create syntax_iterators.py Replica of spacy/lang/fr/syntax_iterators.py * Added import statements for SYNTAX_ITERATORS * Create gustavengstrom.md * Added "dobj" to list of labels in noun_chunks method and a test_noun_chunks method to the Swedish language model. * Delete README-checkpoint.md Co-authored-by: Gustav Co-authored-by: Ines Montani --- .github/contributors/gustavengstrom.md | 106 ++++++++++++++++++++++++ spacy/lang/sv/__init__.py | 2 + spacy/lang/sv/syntax_iterators.py | 50 +++++++++++ spacy/tests/lang/sv/test_noun_chunks.py | 48 +++++++++++ 4 files changed, 206 insertions(+) create mode 100644 .github/contributors/gustavengstrom.md create mode 100644 spacy/lang/sv/syntax_iterators.py create mode 100644 spacy/tests/lang/sv/test_noun_chunks.py diff --git a/.github/contributors/gustavengstrom.md b/.github/contributors/gustavengstrom.md new file mode 100644 index 000000000..d3e0da5a4 --- /dev/null +++ b/.github/contributors/gustavengstrom.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 | Gustav Engström | +| Company name (if applicable) | Davcon | +| Title or role (if applicable) | Data scientis | +| Date | 2019-10-10 | +| GitHub username | gustavengstrom | +| Website (optional) | | diff --git a/spacy/lang/sv/__init__.py b/spacy/lang/sv/__init__.py index 55a0b97bc..671eefca0 100644 --- a/spacy/lang/sv/__init__.py +++ b/spacy/lang/sv/__init__.py @@ -14,6 +14,7 @@ from ..norm_exceptions import BASE_NORMS from ...language import Language from ...attrs import LANG, NORM from ...util import update_exc, add_lookups +from .syntax_iterators import SYNTAX_ITERATORS class SwedishDefaults(Language.Defaults): @@ -29,6 +30,7 @@ class SwedishDefaults(Language.Defaults): suffixes = TOKENIZER_SUFFIXES stop_words = STOP_WORDS morph_rules = MORPH_RULES + syntax_iterators = SYNTAX_ITERATORS class Swedish(Language): diff --git a/spacy/lang/sv/syntax_iterators.py b/spacy/lang/sv/syntax_iterators.py new file mode 100644 index 000000000..7a82e6b59 --- /dev/null +++ b/spacy/lang/sv/syntax_iterators.py @@ -0,0 +1,50 @@ +# coding: utf8 +from __future__ import unicode_literals + +from ...symbols import NOUN, PROPN, PRON + + +def noun_chunks(obj): + """ + Detect base noun phrases from a dependency parse. Works on both Doc and Span. + """ + labels = [ + "nsubj", + "nsubj:pass", + "dobj", + "obj", + "iobj", + "ROOT", + "appos", + "nmod", + "nmod:poss", + ] + doc = obj.doc # Ensure works on both Doc and Span. + np_deps = [doc.vocab.strings[label] for label in labels] + conj = doc.vocab.strings.add("conj") + np_label = doc.vocab.strings.add("NP") + seen = set() + for i, word in enumerate(obj): + if word.pos not in (NOUN, PROPN, PRON): + continue + # Prevent nested chunks from being produced + if word.i in seen: + continue + if word.dep in np_deps: + if any(w.i in seen for w in word.subtree): + continue + seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1)) + yield word.left_edge.i, word.right_edge.i + 1, np_label + elif word.dep == conj: + head = word.head + while head.dep == conj and head.head.i < head.i: + head = head.head + # If the head is an NP, and we're coordinated to it, we're an NP + if head.dep in np_deps: + if any(w.i in seen for w in word.subtree): + continue + seen.update(j for j in range(word.left_edge.i, word.right_edge.i + 1)) + yield word.left_edge.i, word.right_edge.i + 1, np_label + + +SYNTAX_ITERATORS = {"noun_chunks": noun_chunks} diff --git a/spacy/tests/lang/sv/test_noun_chunks.py b/spacy/tests/lang/sv/test_noun_chunks.py new file mode 100644 index 000000000..aafe69139 --- /dev/null +++ b/spacy/tests/lang/sv/test_noun_chunks.py @@ -0,0 +1,48 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import pytest +from spacy.lang.sv.syntax_iterators import SYNTAX_ITERATORS +from ...util import get_doc + +SV_NP_TEST_EXAMPLES = [ + ( + "En student läste en bok", # A student read a book + ["DET", "NOUN", "VERB", "DET", "NOUN"], + ["det", "nsubj", "ROOT", "det", "dobj"], + [1, 1, 0, 1, -2], + ["En student", "en bok"], + ), + ( + "Studenten läste den bästa boken.", # The student read the best book + ["NOUN", "VERB", "DET", "ADJ", "NOUN", "PUNCT"], + ["nsubj", "ROOT", "det", "amod", "dobj", "punct"], + [1, 0, 2, 1, -3, -4], + ["Studenten", "den bästa boken"], + ), + ( + "De samvetslösa skurkarna hade stulit de största juvelerna på söndagen", # The remorseless crooks had stolen the largest jewels that sunday + ["DET", "ADJ", "NOUN", "VERB", "VERB", "DET", "ADJ", "NOUN", "ADP", "NOUN"], + ["det", "amod", "nsubj", "aux", "root", "det", "amod", "dobj", "case", "nmod"], + [2, 1, 2, 1, 0, 2, 1, -3, 1, -5], + ["De samvetslösa skurkarna", "de största juvelerna", "på söndagen"], + ), +] + + +@pytest.mark.parametrize( + "text,pos,deps,heads,expected_noun_chunks", SV_NP_TEST_EXAMPLES +) +def test_sv_noun_chunks(sv_tokenizer, text, pos, deps, heads, expected_noun_chunks): + tokens = sv_tokenizer(text) + + assert len(heads) == len(pos) + doc = get_doc( + tokens.vocab, words=[t.text for t in tokens], heads=heads, deps=deps, pos=pos + ) + + noun_chunks = list(doc.noun_chunks) + assert len(noun_chunks) == len(expected_noun_chunks) + for i, np in enumerate(noun_chunks): + assert np.text == expected_noun_chunks[i] +