@inproceedings{liu-etal-2023-sae,
title = "{SAE}-{NTM}: Sentence-Aware Encoder for Neural Topic Modeling",
author = "Liu, Hao and
Gao, Jingsheng and
Xiang, Suncheng and
Liu, Ting and
Fu, Yuzhuo",
editor = "Strube, Michael and
Braud, Chloe and
Hardmeier, Christian and
Li, Junyi Jessy and
Loaiciga, Sharid and
Zeldes, Amir",
booktitle = "Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.codi-1.14",
doi = "10.18653/v1/2023.codi-1.14",
pages = "106--111",
abstract = "Incorporating external knowledge, such as pre-trained language models (PLMs), into neural topic modeling has achieved great success in recent years. However, employing PLMs for topic modeling generally ignores the maximum sequence length of PLMs and the interaction between external knowledge and bag-of-words (BOW). To this end, we propose a sentence-aware encoder for neural topic modeling, which adopts fine-grained sentence embeddings as external knowledge to entirely utilize the semantic information of input documents. We introduce sentence-aware attention for document representation, where BOW enables the model to attend on topical sentences that convey topic-related cues. Experiments on three benchmark datasets show that our framework outperforms other state-of-the-art neural topic models in topic coherence. Further, we demonstrate that the proposed approach can yield better latent document-topic features through improvement on the document classification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2023-sae">
<titleInfo>
<title>SAE-NTM: Sentence-Aware Encoder for Neural Topic Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingsheng</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suncheng</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuzhuo</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Strube</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chloe</namePart>
<namePart type="family">Braud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharid</namePart>
<namePart type="family">Loaiciga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zeldes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Incorporating external knowledge, such as pre-trained language models (PLMs), into neural topic modeling has achieved great success in recent years. However, employing PLMs for topic modeling generally ignores the maximum sequence length of PLMs and the interaction between external knowledge and bag-of-words (BOW). To this end, we propose a sentence-aware encoder for neural topic modeling, which adopts fine-grained sentence embeddings as external knowledge to entirely utilize the semantic information of input documents. We introduce sentence-aware attention for document representation, where BOW enables the model to attend on topical sentences that convey topic-related cues. Experiments on three benchmark datasets show that our framework outperforms other state-of-the-art neural topic models in topic coherence. Further, we demonstrate that the proposed approach can yield better latent document-topic features through improvement on the document classification.</abstract>
<identifier type="citekey">liu-etal-2023-sae</identifier>
<identifier type="doi">10.18653/v1/2023.codi-1.14</identifier>
<location>
<url>https://aclanthology.org/2023.codi-1.14</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>106</start>
<end>111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SAE-NTM: Sentence-Aware Encoder for Neural Topic Modeling
%A Liu, Hao
%A Gao, Jingsheng
%A Xiang, Suncheng
%A Liu, Ting
%A Fu, Yuzhuo
%Y Strube, Michael
%Y Braud, Chloe
%Y Hardmeier, Christian
%Y Li, Junyi Jessy
%Y Loaiciga, Sharid
%Y Zeldes, Amir
%S Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F liu-etal-2023-sae
%X Incorporating external knowledge, such as pre-trained language models (PLMs), into neural topic modeling has achieved great success in recent years. However, employing PLMs for topic modeling generally ignores the maximum sequence length of PLMs and the interaction between external knowledge and bag-of-words (BOW). To this end, we propose a sentence-aware encoder for neural topic modeling, which adopts fine-grained sentence embeddings as external knowledge to entirely utilize the semantic information of input documents. We introduce sentence-aware attention for document representation, where BOW enables the model to attend on topical sentences that convey topic-related cues. Experiments on three benchmark datasets show that our framework outperforms other state-of-the-art neural topic models in topic coherence. Further, we demonstrate that the proposed approach can yield better latent document-topic features through improvement on the document classification.
%R 10.18653/v1/2023.codi-1.14
%U https://aclanthology.org/2023.codi-1.14
%U https://doi.org/10.18653/v1/2023.codi-1.14
%P 106-111
Markdown (Informal)
[SAE-NTM: Sentence-Aware Encoder for Neural Topic Modeling](https://aclanthology.org/2023.codi-1.14) (Liu et al., CODI 2023)
ACL
- Hao Liu, Jingsheng Gao, Suncheng Xiang, Ting Liu, and Yuzhuo Fu. 2023. SAE-NTM: Sentence-Aware Encoder for Neural Topic Modeling. In Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023), pages 106–111, Toronto, Canada. Association for Computational Linguistics.