lda2vec

Topic model

A framework for creating interpretable natural language models by combining word embeddings and topic modeling.

GitHub

3k stars
119 watching
627 forks
Language: Python
last commit: about 3 years ago

Related projects:

Repository Description Stars
ddangelov/top2vec A Python library that provides a deep learning-based approach to topic modeling and semantic search by jointly embedding topics, documents, and words. 2,943
pair-code/lit An interactive tool for analyzing and understanding machine learning models 3,492
vefstathiou/so_word2vec This is a word embedding model trained on Stack Overflow posts for use in natural language processing tasks. 40
dselivanov/text2vec An R package providing efficient tools for text analysis and natural language processing tasks. 853
wikipedia2vec/wikipedia2vec A tool for learning vector representations of words and entities from Wikipedia text data. 940
tca19/dict2vec A framework to learn word embeddings using lexical dictionaries 115
danieldk/go2vec A package for reading and analyzing word embeddings from the word2vec format in Go. 56
alexandres/lexvec An implementation of a word embedding model that uses character n-grams and achieves state-of-the-art results in multiple NLP tasks 803
ealdent/lda-ruby A Ruby wrapper around an existing C implementation of Latent Dirichlet Allocation (LDA) for topic modeling in natural language processing. 133
dalinvip/cw2vec A software framework for learning Chinese word embeddings with stroke n-gram information 274
ncbi-nlp/biosentvec Pre-trained word and sentence embeddings for biomedical text analysis 578
wse-research/loris-llm-generated-representations-of-sparql-queries Generates natural language representations of SPARQL queries to facilitate understanding and mitigate errors in large knowledge graphs 3
jalammar/ecco An interactive visualization library for exploring and understanding transformer-based language models 1,985
primaryobjects/lda A JavaScript library that uses Latent Dirichlet allocation to model topics in text data 291
mmihaltz/word2vec-googlenews-vectors A repository hosting pre-trained word vector model (3 million 300-dimension English word vectors) from the Google News corpus. 516