A Disentangled Adversarial Neural Topic Model for Separating Opinions from Plots in User Reviews

Gabriele Pergola, Lin Gui, Yulan He


Abstract
The flexibility of the inference process in Variational Autoencoders (VAEs) has recently led to revising traditional probabilistic topic models giving rise to Neural Topic Models (NTM). Although these approaches have achieved significant results, surprisingly very little work has been done on how to disentangle the latent topics. Existing topic models when applied to reviews may extract topics associated with writers’ subjective opinions mixed with those related to factual descriptions such as plot summaries in movie and book reviews. It is thus desirable to automatically separate opinion topics from plot/neutral ones enabling a better interpretability. In this paper, we propose a neural topic model combined with adversarial training to disentangle opinion topics from plot and neutral ones. We conduct an extensive experimental assessment introducing a new collection of movie and book reviews paired with their plots, namely MOBO dataset, showing an improved coherence and variety of topics, a consistent disentanglement rate, and sentiment classification performance superior to other supervised topic models.
Anthology ID:
2021.naacl-main.228
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2870–2883
Language:
URL:
https://aclanthology.org/2021.naacl-main.228
DOI:
10.18653/v1/2021.naacl-main.228
Bibkey:
Cite (ACL):
Gabriele Pergola, Lin Gui, and Yulan He. 2021. A Disentangled Adversarial Neural Topic Model for Separating Opinions from Plots in User Reviews. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2870–2883, Online. Association for Computational Linguistics.
Cite (Informal):
A Disentangled Adversarial Neural Topic Model for Separating Opinions from Plots in User Reviews (Pergola et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.228.pdf
Video:
 https://aclanthology.org/2021.naacl-main.228.mp4
Code
 gabrer/diatom
Data
IMDb Movie Reviews