Diversity-Aware Coherence Loss for Improving Neural Topic Models

Raymond Li, Felipe Gonzalez-Pizarro, Linzi Xing, Gabriel Murray, Giuseppe Carenini


Abstract
The standard approach for neural topic modeling uses a variational autoencoder (VAE) framework that jointly minimizes the KL divergence between the estimated posterior and prior, in addition to the reconstruction loss. Since neural topic models are trained by recreating individual input documents, they do not explicitly capture the coherence between words on the corpus level. In this work, we propose a novel diversity-aware coherence loss that encourages the model to learn corpus-level coherence scores while maintaining high diversity between topics. Experimental results on multiple datasets show that our method significantly improves the performance of neural topic models without requiring any pretraining or additional parameters.
Anthology ID:
2023.acl-short.145
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1710–1722
Language:
URL:
https://aclanthology.org/2023.acl-short.145
DOI:
10.18653/v1/2023.acl-short.145
Bibkey:
Cite (ACL):
Raymond Li, Felipe Gonzalez-Pizarro, Linzi Xing, Gabriel Murray, and Giuseppe Carenini. 2023. Diversity-Aware Coherence Loss for Improving Neural Topic Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1710–1722, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Diversity-Aware Coherence Loss for Improving Neural Topic Models (Li et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.acl-short.145.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-5/2023.acl-short.145.mp4