@inproceedings{zhang-etal-2022-pre,
title = "Pre-training and Fine-tuning Neural Topic Model: A Simple yet Effective Approach to Incorporating External Knowledge",
author = "Zhang, Linhai and
Hu, Xuemeng and
Wang, Boyu and
Zhou, Deyu and
Zhang, Qian-Wen and
Cao, Yunbo",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.413/",
doi = "10.18653/v1/2022.acl-long.413",
pages = "5980--5989",
abstract = "Recent years have witnessed growing interests in incorporating external knowledge such as pre-trained word embeddings (PWEs) or pre-trained language models (PLMs) into neural topic modeling. However, we found that employing PWEs and PLMs for topic modeling only achieved limited performance improvements but with huge computational overhead. In this paper, we propose a novel strategy to incorporate external knowledge into neural topic modeling where the neural topic model is pre-trained on a large corpus and then fine-tuned on the target dataset. Experiments have been conducted on three datasets and results show that the proposed approach significantly outperforms both current state-of-the-art neural topic models and some topic modeling approaches enhanced with PWEs or PLMs. Moreover, further study shows that the proposed approach greatly reduces the need for the huge size of training data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-pre">
<titleInfo>
<title>Pre-training and Fine-tuning Neural Topic Model: A Simple yet Effective Approach to Incorporating External Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Linhai</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuemeng</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian-Wen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunbo</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent years have witnessed growing interests in incorporating external knowledge such as pre-trained word embeddings (PWEs) or pre-trained language models (PLMs) into neural topic modeling. However, we found that employing PWEs and PLMs for topic modeling only achieved limited performance improvements but with huge computational overhead. In this paper, we propose a novel strategy to incorporate external knowledge into neural topic modeling where the neural topic model is pre-trained on a large corpus and then fine-tuned on the target dataset. Experiments have been conducted on three datasets and results show that the proposed approach significantly outperforms both current state-of-the-art neural topic models and some topic modeling approaches enhanced with PWEs or PLMs. Moreover, further study shows that the proposed approach greatly reduces the need for the huge size of training data.</abstract>
<identifier type="citekey">zhang-etal-2022-pre</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.413</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.413/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>5980</start>
<end>5989</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pre-training and Fine-tuning Neural Topic Model: A Simple yet Effective Approach to Incorporating External Knowledge
%A Zhang, Linhai
%A Hu, Xuemeng
%A Wang, Boyu
%A Zhou, Deyu
%A Zhang, Qian-Wen
%A Cao, Yunbo
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F zhang-etal-2022-pre
%X Recent years have witnessed growing interests in incorporating external knowledge such as pre-trained word embeddings (PWEs) or pre-trained language models (PLMs) into neural topic modeling. However, we found that employing PWEs and PLMs for topic modeling only achieved limited performance improvements but with huge computational overhead. In this paper, we propose a novel strategy to incorporate external knowledge into neural topic modeling where the neural topic model is pre-trained on a large corpus and then fine-tuned on the target dataset. Experiments have been conducted on three datasets and results show that the proposed approach significantly outperforms both current state-of-the-art neural topic models and some topic modeling approaches enhanced with PWEs or PLMs. Moreover, further study shows that the proposed approach greatly reduces the need for the huge size of training data.
%R 10.18653/v1/2022.acl-long.413
%U https://aclanthology.org/2022.acl-long.413/
%U https://doi.org/10.18653/v1/2022.acl-long.413
%P 5980-5989
Markdown (Informal)
[Pre-training and Fine-tuning Neural Topic Model: A Simple yet Effective Approach to Incorporating External Knowledge](https://aclanthology.org/2022.acl-long.413/) (Zhang et al., ACL 2022)
ACL