explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-11-04 09:57:26 +03:00
Code Issues Packages Projects Releases Wiki Activity

added crosslingual coreference to spacy universe without additional commits (#10580)

Browse Source 
* added crosslingual coreference to spacy universe

* Updated example to introduce batching example.

Co-authored-by: David Berenstein <david.berenstein@pandoraintelligence.com>
This commit is contained in:
David Berenstein 2022-04-08 08:23:58 +02:00 committed by Adriane Boyd
parent 1a6816f477
commit ce8a9f00b6
1 changed files with 60 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
website/meta/universe.json
View File

@ -2704,6 +2704,66 @@
],
"spacy_version": 3
},
{
"id": "crosslingualcoreference",
"title": "Crosslingual Coreference",
"slogan": "One multi-lingual coreference model to rule them all!",
"description": "Coreference is amazing but the data required for training a model is very scarce. In our case, the available training for non-English languages also data proved to be poorly annotated. Crosslingual Coreference therefore uses the assumption a trained model with English data and cross-lingual embeddings should work for other languages with similar sentence structure. Verified to work quite well for at least (EN, NL, DK, FR, DE).",
"github": "pandora-intelligence/crosslingual-coreference",
"pip": "crosslingual-coreference",
"thumb": "https://raw.githubusercontent.com/Pandora-Intelligence/crosslingual-coreference/master/img/logo.png",
"image": "https://raw.githubusercontent.com/Pandora-Intelligence/crosslingual-coreference/master/img/example_total.png",
"code_example": [
"import spacy",
"import crosslingual_coreference",
"",
"text = \"\"\"",
" Do not forget about Momofuku Ando!",
" He created instant noodles in Osaka.",
" At that location, Nissin was founded.",
" Many students survived by eating these noodles, but they don't even know him.\"\"\"",
"",
"# use any model that has internal spacy embeddings",
"nlp = spacy.load('en_core_web_sm')",
"nlp.add_pipe(",
" \"xx_coref\", config={\"chunk_size\": 2500, \"chunk_overlap\": 2, \"device\": 0})",
")",
"",
"doc = nlp(text)",
"",
"print(doc._.coref_clusters)",
"# Output",
"#",
"# [[[4, 5], [7, 7], [27, 27], [36, 36]],",
"# [[12, 12], [15, 16]],",
"# [[9, 10], [27, 28]],",
"# [[22, 23], [31, 31]]]",
"print(doc._.resolved_text)",
"# Output",
"#",
"# Do not forget about Momofuku Ando!",
"# Momofuku Ando created instant noodles in Osaka.",
"# At Osaka, Nissin was founded.",
"# Many students survived by eating instant noodles,",
"# but Many students don't even know Momofuku Ando."
],
"author": "David Berenstein",
"author_links": {
"github": "davidberenstein1957",
"website": "https://www.linkedin.com/in/david-berenstein-1bab11105/"
},
"category": [
"pipeline",
"standalone"
],
"tags": [
"coreference",
"multi-lingual",
"cross-lingual",
"allennlp"
],
"spacy_version": 3
},
{
"id": "blackstone",
"title": "Blackstone",