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

Sentence transformers added to spaCy universe (#5814)

Browse Source 
* fix details for spacy-universal-sentence-encoder

* added sentence-transformers
This commit is contained in:
Martino Mensio 2020-07-27 09:44:33 +02:00 committed by Adriane Boyd
parent 1bfc177b10
commit b57b994d38
1 changed files with 28 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
website/meta/universe.json
View File

@ -1,5 +1,30 @@
{
"resources": [
{
"id": "spacy-sentence-bert",
"title": "SpaCy - sentence-transformers",
"slogan": "Pipelines for pretrained sentence-transformers (BERT, RoBERTa, XLM-RoBERTa & Co.) directly within SpaCy",
"description": "This library lets you use the embeddings from [sentence-transformers](https://github.com/UKPLab/sentence-transformers) of Docs, Spans and Tokens directly from spaCy. Most models are for the english language but three of them are multilingual.",
"github": "MartinoMensio/spacy-sentence-bert",
"pip": "spacy-sentence-bert",
"code_example": [
"import spacy_sentence_bert",
"# load one of the models listed at https://github.com/MartinoMensio/spacy-sentence-bert/",
"nlp = spacy_sentence_bert.load_model('en_roberta_large_nli_stsb_mean_tokens')",
"# get two documents",
"doc_1 = nlp('Hi there, how are you?')",
"doc_2 = nlp('Hello there, how are you doing today?')",
"# use the similarity method that is based on the vectors, on Doc, Span or Token",
"print(doc_1.similarity(doc_2[0:7]))"
],
"category": ["models", "pipeline"],
"author": "Martino Mensio",
"author_links": {
"twitter": "MartinoMensio",
"github": "MartinoMensio",
"website": "https://martinomensio.github.io"
}
},
{
"id": "spacy-streamlit",
"title": "spacy-streamlit",
@ -58,10 +83,11 @@
"title": "SpaCy - Universal Sentence Encoder",
"slogan": "Make use of Google's Universal Sentence Encoder directly within SpaCy",
"description": "This library lets you use Universal Sentence Encoder embeddings of Docs, Spans and Tokens directly from TensorFlow Hub",
"github": "MartinoMensio/spacy-universal-sentence-encoder-tfhub",
"github": "MartinoMensio/spacy-universal-sentence-encoder",
"pip": "spacy-universal-sentence-encoder",
"code_example": [
"import spacy_universal_sentence_encoder",
"load one of the models: ['en_use_md', 'en_use_lg', 'xx_use_md', 'xx_use_lg']",
"# load one of the models: ['en_use_md', 'en_use_lg', 'xx_use_md', 'xx_use_lg']",
"nlp = spacy_universal_sentence_encoder.load_model('en_use_lg')",
"# get two documents",
"doc_1 = nlp('Hi there, how are you?')",