@inproceedings{shibuya-utsuro-2024-embedded,
title = "Embedded Topic Models Enhanced by Wikification",
author = "Shibuya, Takashi and
Utsuro, Takehito",
editor = "Lucie-Aim{\'e}e, Lucie and
Fan, Angela and
Gwadabe, Tajuddeen and
Johnson, Isaac and
Petroni, Fabio and
van Strien, Daniel",
booktitle = "Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wikinlp-1.13",
pages = "80--90",
abstract = "Topic modeling analyzes a collection of documents to learn meaningful patterns of words.However, previous topic models consider only the spelling of words and do not take into consideration the polysemy of words.In this study, we incorporate the Wikipedia knowledge into a neural topic model to make it aware of named entities.We evaluate our method on two datasets, 1) news articles of New York Times and 2) the AIDA-CoNLL dataset.Our experiments show that our method improves the performance of neural topic models in generalizability.Moreover, we analyze frequent words in each topic and the temporal dependencies between topics to demonstrate that our entity-aware topic models can capture the time-series development of topics well.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shibuya-utsuro-2024-embedded">
<titleInfo>
<title>Embedded Topic Models Enhanced by Wikification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Shibuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takehito</namePart>
<namePart type="family">Utsuro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Lucie-Aimée</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tajuddeen</namePart>
<namePart type="family">Gwadabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaac</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Petroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">van Strien</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Topic modeling analyzes a collection of documents to learn meaningful patterns of words.However, previous topic models consider only the spelling of words and do not take into consideration the polysemy of words.In this study, we incorporate the Wikipedia knowledge into a neural topic model to make it aware of named entities.We evaluate our method on two datasets, 1) news articles of New York Times and 2) the AIDA-CoNLL dataset.Our experiments show that our method improves the performance of neural topic models in generalizability.Moreover, we analyze frequent words in each topic and the temporal dependencies between topics to demonstrate that our entity-aware topic models can capture the time-series development of topics well.</abstract>
<identifier type="citekey">shibuya-utsuro-2024-embedded</identifier>
<location>
<url>https://aclanthology.org/2024.wikinlp-1.13</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>80</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Embedded Topic Models Enhanced by Wikification
%A Shibuya, Takashi
%A Utsuro, Takehito
%Y Lucie-Aimée, Lucie
%Y Fan, Angela
%Y Gwadabe, Tajuddeen
%Y Johnson, Isaac
%Y Petroni, Fabio
%Y van Strien, Daniel
%S Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F shibuya-utsuro-2024-embedded
%X Topic modeling analyzes a collection of documents to learn meaningful patterns of words.However, previous topic models consider only the spelling of words and do not take into consideration the polysemy of words.In this study, we incorporate the Wikipedia knowledge into a neural topic model to make it aware of named entities.We evaluate our method on two datasets, 1) news articles of New York Times and 2) the AIDA-CoNLL dataset.Our experiments show that our method improves the performance of neural topic models in generalizability.Moreover, we analyze frequent words in each topic and the temporal dependencies between topics to demonstrate that our entity-aware topic models can capture the time-series development of topics well.
%U https://aclanthology.org/2024.wikinlp-1.13
%P 80-90
Markdown (Informal)
[Embedded Topic Models Enhanced by Wikification](https://aclanthology.org/2024.wikinlp-1.13) (Shibuya & Utsuro, WikiNLP 2024)
ACL
- Takashi Shibuya and Takehito Utsuro. 2024. Embedded Topic Models Enhanced by Wikification. In Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia, pages 80–90, Miami, Florida, USA. Association for Computational Linguistics.