Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Xiaobao, Dong, Xinshuai, Pan, Liangming, Nguyen, Thong, Luu, Anh Tuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916263404503040
author Wu, Xiaobao
Dong, Xinshuai
Pan, Liangming
Nguyen, Thong
Luu, Anh Tuan
author_facet Wu, Xiaobao
Dong, Xinshuai
Pan, Liangming
Nguyen, Thong
Luu, Anh Tuan
contents Dynamic topic models track the evolution of topics in sequential documents, which have derived various applications like trend analysis and opinion mining. However, existing models suffer from repetitive topic and unassociated topic issues, failing to reveal the evolution and hindering further applications. To address these issues, we break the tradition of simply chaining topics in existing work and propose a novel neural \modelfullname. We introduce a new evolution-tracking contrastive learning method that builds the similarity relations among dynamic topics. This not only tracks topic evolution but also maintains topic diversity, mitigating the repetitive topic issue. To avoid unassociated topics, we further present an unassociated word exclusion method that consistently excludes unassociated words from discovered topics. Extensive experiments demonstrate our model significantly outperforms state-of-the-art baselines, tracking topic evolution with high-quality topics, showing better performance on downstream tasks, and remaining robust to the hyperparameter for evolution intensities. Our code is available at https://github.com/bobxwu/CFDTM .
format Preprint
id arxiv_https___arxiv_org_abs_2405_17957
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion
Wu, Xiaobao
Dong, Xinshuai
Pan, Liangming
Nguyen, Thong
Luu, Anh Tuan
Computation and Language
Artificial Intelligence
Dynamic topic models track the evolution of topics in sequential documents, which have derived various applications like trend analysis and opinion mining. However, existing models suffer from repetitive topic and unassociated topic issues, failing to reveal the evolution and hindering further applications. To address these issues, we break the tradition of simply chaining topics in existing work and propose a novel neural \modelfullname. We introduce a new evolution-tracking contrastive learning method that builds the similarity relations among dynamic topics. This not only tracks topic evolution but also maintains topic diversity, mitigating the repetitive topic issue. To avoid unassociated topics, we further present an unassociated word exclusion method that consistently excludes unassociated words from discovered topics. Extensive experiments demonstrate our model significantly outperforms state-of-the-art baselines, tracking topic evolution with high-quality topics, showing better performance on downstream tasks, and remaining robust to the hyperparameter for evolution intensities. Our code is available at https://github.com/bobxwu/CFDTM .
title Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.17957