Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec

Christopher E Moody
5/6/2016
cs.CL

Official code: cemoody/lda2vec (3,169 stars, MIT, last commit 2021-11-16).

Abstract

Distributed dense word vectors have been shown to be effective at capturing token-level semantic and syntactic regularities in language, while topic models can form interpretable representations over documents. In this work, we describe lda2vec, a model that learns dense word vectors jointly with Dirichlet-distributed latent document-level mixtures of topic vectors. In contrast to continuous dense document representations, this formulation produces sparse, interpretable document mixtures through a non-negative simplex constraint. Our method is simple to incorporate into existing automatic differentiation frameworks and allows for unsupervised document representations geared for use by scientists while simultaneously learning word vectors and the linear relationships between them.

View on arXivView PDF

Code Implementations(1)

cemoody/lda2vecOfficial100%
MIT
3,169621PythonDec 25, 20154 years agoMIT

Similar Papers

Sparse Overcomplete Word Vector Representations

82% match1 repo572015

Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)

79% match1 repo1342024

E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time

79% match2025

Interpretable Syntactic Representations Enable Hierarchical Word Vectors

78% match2024

From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models

78% match2024

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

78% match1 repo1.7k2024

Cite this paper

@article{moody2016mixing,
  title  = {Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec},
  author = {Christopher E Moody},
  year   = {2016},
  eprint = {1605.02019},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1605.02019}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1605.02019.svg)](https://codeofpaper.com/paper/1605.02019)

Discussion