Topic Modeling in Embedding Spaces

Adji B. Dieng, Francisco J. R. Ruiz, David M. Blei


Abstract
Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the embedded topic model (etm), a generative model of documents that marries traditional topic models with word embeddings. More specifically, the etm models each word with a categorical distribution whose natural parameter is the inner product between the word’s embedding and an embedding of its assigned topic. To fit the etm, we develop an efficient amortized variational inference algorithm. The etm discovers interpretable topics even with large vocabularies that include rare words and stop words. It outperforms existing document models, such as latent Dirichlet allocation, in terms of both topic quality and predictive performance.
Anthology ID:
2020.tacl-1.29
Volume:
Transactions of the Association for Computational Linguistics, Volume 8
Month:
Year:
2020
Address:
Cambridge, MA
Editors:
Mark Johnson, Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
439–453
Language:
URL:
https://aclanthology.org/2020.tacl-1.29
DOI:
10.1162/tacl_a_00325
Bibkey:
Cite (ACL):
Adji B. Dieng, Francisco J. R. Ruiz, and David M. Blei. 2020. Topic Modeling in Embedding Spaces. Transactions of the Association for Computational Linguistics, 8:439–453.
Cite (Informal):
Topic Modeling in Embedding Spaces (Dieng et al., TACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.tacl-1.29.pdf
Code
 adjidieng/ETM +  additional community code
Data
20NewsGroupsAG News