diff --git a/.github/contributors/gtoffoli.md b/.github/contributors/gtoffoli.md new file mode 100644 index 000000000..5d5d712a2 --- /dev/null +++ b/.github/contributors/gtoffoli.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 | Giovanni Toffoli | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 2021-05-12 | +| GitHub username | gtoffoli | +| Website (optional) | | diff --git a/spacy/lang/it/__init__.py b/spacy/lang/it/__init__.py index 25cbaa651..672a8698e 100644 --- a/spacy/lang/it/__init__.py +++ b/spacy/lang/it/__init__.py @@ -1,7 +1,11 @@ +from typing import Optional +from thinc.api import Model + from .stop_words import STOP_WORDS from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES from ...language import Language +from .lemmatizer import ItalianLemmatizer class ItalianDefaults(Language.Defaults): @@ -16,4 +20,16 @@ class Italian(Language): Defaults = ItalianDefaults +@Italian.factory( + "lemmatizer", + assigns=["token.lemma"], + default_config={"model": None, "mode": "pos_lookup", "overwrite": False}, + default_score_weights={"lemma_acc": 1.0}, +) +def make_lemmatizer( + nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool +): + return ItalianLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite) + + __all__ = ["Italian"] diff --git a/spacy/lang/it/lemmatizer.py b/spacy/lang/it/lemmatizer.py new file mode 100644 index 000000000..fced97d35 --- /dev/null +++ b/spacy/lang/it/lemmatizer.py @@ -0,0 +1,132 @@ +from typing import List, Dict, Tuple + +from ...pipeline import Lemmatizer +from ...tokens import Token + + + +class ItalianLemmatizer(Lemmatizer): + """This lemmatizer was adapted from the Polish one (version of April 2021). + It implements lookup lemmatization based on the morphological lexicon + morph-it (Baroni and Zanchetta). The table lemma_lookup with non-POS-aware + entries is used as a backup for words that aren't handled by morph-it.""" + @classmethod + def get_lookups_config(cls, mode: str) -> Tuple[List[str], List[str]]: + if mode == "pos_lookup": + required = [ + "lemma_lookup_num", + "lemma_lookup_det", + "lemma_lookup_adp", + "lemma_lookup_adj", + "lemma_lookup_noun", + "lemma_lookup_pron", + "lemma_lookup_verb", + "lemma_lookup_aux", + "lemma_lookup_adv", + "lemma_lookup_other", + "lemma_lookup", + ] + return (required, []) + else: + return super().get_lookups_config(mode) + + def pos_lookup_lemmatize(self, token: Token) -> List[str]: + string = token.text + univ_pos = token.pos_ + morphology = token.morph.to_dict() + lookup_pos = univ_pos.lower() + if univ_pos == "PROPN": + lookup_pos = "noun" + elif univ_pos == "PART": + lookup_pos = "pron" + lookup_table = self.lookups.get_table("lemma_lookup_" + lookup_pos, {}) + if univ_pos == "NOUN": + return self.lemmatize_noun(string, morphology, lookup_table) + else: + if univ_pos != "PROPN": + string = string.lower() + if univ_pos == "DET": + return self.lemmatize_det(string, morphology, lookup_table) + elif univ_pos == "PRON": + return self.lemmatize_pron(string, morphology, lookup_table) + elif univ_pos == "ADP": + return self.lemmatize_adp(string, morphology, lookup_table) + elif univ_pos == "ADJ": + return self.lemmatize_adj(string, morphology, lookup_table) + else: + lemma = lookup_table.get(string, "") + if not lemma: + lookup_table = self.lookups.get_table("lemma_lookup_other") + lemma = lookup_table.get(string, "") + if not lemma: + lookup_table = self.lookups.get_table( + "lemma_lookup" + ) # "legacy" lookup table + lemma = lookup_table.get(string, string.lower()) + return [lemma] + + def lemmatize_det( + self, string: str, morphology: dict, lookup_table: Dict[str, str] + ) -> List[str]: + if string in [ + "l'", + "lo", + "la", + "i", + "gli", + "le", + ]: + return ["il"] + if string in ["un'", "un", "una"]: + return ["uno"] + return [lookup_table.get(string, string)] + + def lemmatize_pron( + self, string: str, morphology: dict, lookup_table: Dict[str, str] + ) -> List[str]: + if string in [ + "l'", + "li", + "la", + "gli", + "le", + ]: + return ["lo"] + if string in ["un'", "un", "una"]: + return ["uno"] + lemma = lookup_table.get(string, string) + if lemma == "alcun": + lemma = "alcuno" + elif lemma == "qualcun": + lemma = "qualcuno" + return [lemma] + + def lemmatize_adp( + self, string: str, morphology: dict, lookup_table: Dict[str, str] + ) -> List[str]: + if string == "d'": + return ["di"] + return [lookup_table.get(string, string)] + + def lemmatize_adj( + self, string: str, morphology: dict, lookup_table: Dict[str, str] + ) -> List[str]: + lemma = lookup_table.get(string, string) + if lemma == "alcun": + lemma = "alcuno" + elif lemma == "qualcun": + lemma = "qualcuno" + return [lemma] + + def lemmatize_noun( + self, string: str, morphology: dict, lookup_table: Dict[str, str] + ) -> List[str]: + # this method is case-sensitive, in order to work + # for incorrectly tagged proper names + if string != string.lower(): + if string.lower() in lookup_table: + return [lookup_table[string.lower()]] + elif string in lookup_table: + return [lookup_table[string]] + return [string.lower()] + return [lookup_table.get(string, string)]