Tree-Structured Neural Topic Model

Isonuma, Masaru, Mori, Junichiro, Bollegala, Danushka ORCID: 0000-0003-4476-7003 and Sakata, Ichiro (2020) Tree-Structured Neural Topic Model. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020-7 - 2020-7, Seattle, USA.

Text
ACL2020.pdf - Author Accepted Manuscript
Download (509kB) | Preview

Official URL: http://dx.doi.org/10.18653/v1/2020.acl-main.73

Abstract

This paper presents a tree-structured neural topic model, which has a topic distribution over a tree with an infinite number of branches. Our model parameterizes an unbounded ancestral and fraternal topic distribution by applying doubly-recurrent neural networks. With the help of autoencoding variational Bayes, our model improves data scalability and achieves competitive performance when inducing latent topics and tree structures, as compared to a prior tree-structured topic model (Blei et al., 2010). This work extends the tree-structured topic model such that it can be incorporated with neural models for downstream tasks.

Item Type:	Conference or Workshop Item (Unspecified)
Depositing User:	Symplectic Admin
Date Deposited:	13 May 2020 10:23
Last Modified:	15 Mar 2024 02:26
DOI:	10.18653/v1/2020.acl-main.73
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3085260