MartinoMensio/spacy-universal-sentence-encoder
Google USE (Universal Sentence Encoder) for spaCy
This tool helps data scientists and NLP practitioners enhance their text analysis workflows. It takes text inputs like documents, sentences, or individual words and generates high-quality numerical representations (embeddings) that capture meaning. These embeddings are particularly useful for tasks requiring precise understanding of text similarity, making it easier to compare or group pieces of text based on their semantic content.
183 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to generate accurate numerical representations of text for tasks like sentence similarity comparison, text clustering, or information retrieval, especially when working within a spaCy text processing pipeline.
Not ideal if your primary goal is to use BERT-specific embeddings, as this tool focuses on Google's Universal Sentence Encoder models.
Stars
183
Forks
12
Language
Python
License
MIT
Category
Last pushed
Mar 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/MartinoMensio/spacy-universal-sentence-encoder"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shibing624/similarity
similarity: Text similarity calculation Toolkit for Java. 文本相似度计算工具包，java编写，可用于文本相似度计算、情感分析等任务，开箱即用。
eBay/Sequence-Semantic-Embedding
Tools and recipes to train deep learning models and build services for NLP tasks such as text...
RandolphVI/Text-Pairs-Relation-Classification
About Text Pairs (Sentence Level) Classification (Similarity Modeling) Based on Neural Network.
piotrmaciejbednarski/text-similarity-node
High-performance and memory efficient native C++ text similarity algorithms for Node.js
brianrisk/simphile-text-similarity-nlp
Python Text Similarity NLP Libray