@inproceedings{cha-lee-2024-sentencelda,
title = "{S}entence{LDA}: Discriminative and Robust Document Representation with Sentence Level Topic Model",
author = "Cha, Taehun and
Lee, Donghun",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.31",
pages = "521--538",
abstract = "A subtle difference in context results in totally different nuances even for lexically identical words. On the other hand, two words can convey similar meanings given a homogeneous context. As a result, considering only word spelling information is not sufficient to obtain quality text representation. We propose SentenceLDA, a sentence-level topic model. We combine modern SentenceBERT and classical LDA to extend the semantic unit from word to sentence. By extending the semantic unit, we verify that SentenceLDA returns more discriminative document representation than other topic models, while maintaining LDA{'}s elegant probabilistic interpretability. We also verify the robustness of SentenceLDA by comparing the inference results on original and paraphrased texts. Additionally, we implement one possible application of SentenceLDA on corpus-level key opinion mining by applying SentenceLDA on an argumentative corpus, DebateSum.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cha-lee-2024-sentencelda">
<titleInfo>
<title>SentenceLDA: Discriminative and Robust Document Representation with Sentence Level Topic Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taehun</namePart>
<namePart type="family">Cha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donghun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A subtle difference in context results in totally different nuances even for lexically identical words. On the other hand, two words can convey similar meanings given a homogeneous context. As a result, considering only word spelling information is not sufficient to obtain quality text representation. We propose SentenceLDA, a sentence-level topic model. We combine modern SentenceBERT and classical LDA to extend the semantic unit from word to sentence. By extending the semantic unit, we verify that SentenceLDA returns more discriminative document representation than other topic models, while maintaining LDA’s elegant probabilistic interpretability. We also verify the robustness of SentenceLDA by comparing the inference results on original and paraphrased texts. Additionally, we implement one possible application of SentenceLDA on corpus-level key opinion mining by applying SentenceLDA on an argumentative corpus, DebateSum.</abstract>
<identifier type="citekey">cha-lee-2024-sentencelda</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.31</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>521</start>
<end>538</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SentenceLDA: Discriminative and Robust Document Representation with Sentence Level Topic Model
%A Cha, Taehun
%A Lee, Donghun
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F cha-lee-2024-sentencelda
%X A subtle difference in context results in totally different nuances even for lexically identical words. On the other hand, two words can convey similar meanings given a homogeneous context. As a result, considering only word spelling information is not sufficient to obtain quality text representation. We propose SentenceLDA, a sentence-level topic model. We combine modern SentenceBERT and classical LDA to extend the semantic unit from word to sentence. By extending the semantic unit, we verify that SentenceLDA returns more discriminative document representation than other topic models, while maintaining LDA’s elegant probabilistic interpretability. We also verify the robustness of SentenceLDA by comparing the inference results on original and paraphrased texts. Additionally, we implement one possible application of SentenceLDA on corpus-level key opinion mining by applying SentenceLDA on an argumentative corpus, DebateSum.
%U https://aclanthology.org/2024.eacl-long.31
%P 521-538
Markdown (Informal)
[SentenceLDA: Discriminative and Robust Document Representation with Sentence Level Topic Model](https://aclanthology.org/2024.eacl-long.31) (Cha & Lee, EACL 2024)
ACL