iarroyof/sentence_embedding
A sentence embedding method based on weighted series
This project helps data scientists, machine learning engineers, and NLP practitioners easily convert raw text sentences into numerical representations, known as sentence embeddings. You input a list of sentences, and it outputs a matrix of numerical vectors that capture the meaning of each sentence. These embeddings can then be used for tasks like finding similar sentences or categorizing text.
Use this if you need a lightweight, open-source method for generating sentence embeddings that doesn't require pre-existing language resources or complex training, and you want to use popular word embeddings like FastText or GloVe with TF-IDF weighting.
Not ideal if you need state-of-the-art performance on highly nuanced semantic tasks or require embeddings specifically fine-tuned on a very niche domain, which might be better served by large transformer models.
Stars
9
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/iarroyof/sentence_embedding"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dselivanov/text2vec
Fast vectorization, topic modeling, distances and GloVe word embeddings in R.
vzhong/embeddings
Fast, DB Backed pretrained word embeddings for natural language processing.
dccuchile/spanish-word-embeddings
Spanish word embeddings computed with different methods and from different corpora
ncbi-nlp/BioSentVec
BioWordVec & BioSentVec: pre-trained embeddings for biomedical words and sentences
ibrahimsharaf/doc2vec
:notebook: Long(er) text representation and classification using Doc2Vec embeddings