@inproceedings{huang-etal-2021-unsupervised,
title = "Unsupervised Multi-document Summarization for News Corpus with Key Synonyms and Contextual Embeddings",
author = "Huang, Yen-Hao and
Pornvattanavichai, Ratana and
Alvarado, Fernando Henrique Calderon and
Chen, Yi-Shin",
editor = "Lee, Lung-Hao and
Chang, Chia-Hui and
Chen, Kuan-Yu",
booktitle = "Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)",
month = oct,
year = "2021",
address = "Taoyuan, Taiwan",
publisher = "The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)",
url = "https://aclanthology.org/2021.rocling-1.25/",
pages = "192--201",
abstract = "Information overload has been one of the challenges regarding information from the Internet. It is not a matter of information access, instead, the focus had shifted towards the quality of the retrieved data. Particularly in the news domain, multiple outlets report on the same news events but may differ in details. This work considers that different news outlets are more likely to differ in their writing styles and the choice of words, and proposes a method to extract sentences based on their key information by focusing on the shared synonyms in each sentence. Our method also attempts to reduce redundancy through hierarchical clustering and arrange selected sentences on the proposed orderBERT. The results show that the proposed unsupervised framework successfully improves the coverage, coherence, and, meanwhile, reduces the redundancy for a generated summary. Moreover, due to the process of obtaining the dataset, we also propose a data refinement method to alleviate the problems of undesirable texts, which result from the process of automatic scraping."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2021-unsupervised">
<titleInfo>
<title>Unsupervised Multi-document Summarization for News Corpus with Key Synonyms and Contextual Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yen-Hao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ratana</namePart>
<namePart type="family">Pornvattanavichai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="given">Henrique</namePart>
<namePart type="given">Calderon</namePart>
<namePart type="family">Alvarado</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi-Shin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lung-Hao</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuan-Yu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)</publisher>
<place>
<placeTerm type="text">Taoyuan, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Information overload has been one of the challenges regarding information from the Internet. It is not a matter of information access, instead, the focus had shifted towards the quality of the retrieved data. Particularly in the news domain, multiple outlets report on the same news events but may differ in details. This work considers that different news outlets are more likely to differ in their writing styles and the choice of words, and proposes a method to extract sentences based on their key information by focusing on the shared synonyms in each sentence. Our method also attempts to reduce redundancy through hierarchical clustering and arrange selected sentences on the proposed orderBERT. The results show that the proposed unsupervised framework successfully improves the coverage, coherence, and, meanwhile, reduces the redundancy for a generated summary. Moreover, due to the process of obtaining the dataset, we also propose a data refinement method to alleviate the problems of undesirable texts, which result from the process of automatic scraping.</abstract>
<identifier type="citekey">huang-etal-2021-unsupervised</identifier>
<location>
<url>https://aclanthology.org/2021.rocling-1.25/</url>
</location>
<part>
<date>2021-10</date>
<extent unit="page">
<start>192</start>
<end>201</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Multi-document Summarization for News Corpus with Key Synonyms and Contextual Embeddings
%A Huang, Yen-Hao
%A Pornvattanavichai, Ratana
%A Alvarado, Fernando Henrique Calderon
%A Chen, Yi-Shin
%Y Lee, Lung-Hao
%Y Chang, Chia-Hui
%Y Chen, Kuan-Yu
%S Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)
%D 2021
%8 October
%I The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
%C Taoyuan, Taiwan
%F huang-etal-2021-unsupervised
%X Information overload has been one of the challenges regarding information from the Internet. It is not a matter of information access, instead, the focus had shifted towards the quality of the retrieved data. Particularly in the news domain, multiple outlets report on the same news events but may differ in details. This work considers that different news outlets are more likely to differ in their writing styles and the choice of words, and proposes a method to extract sentences based on their key information by focusing on the shared synonyms in each sentence. Our method also attempts to reduce redundancy through hierarchical clustering and arrange selected sentences on the proposed orderBERT. The results show that the proposed unsupervised framework successfully improves the coverage, coherence, and, meanwhile, reduces the redundancy for a generated summary. Moreover, due to the process of obtaining the dataset, we also propose a data refinement method to alleviate the problems of undesirable texts, which result from the process of automatic scraping.
%U https://aclanthology.org/2021.rocling-1.25/
%P 192-201
Markdown (Informal)
[Unsupervised Multi-document Summarization for News Corpus with Key Synonyms and Contextual Embeddings](https://aclanthology.org/2021.rocling-1.25/) (Huang et al., ROCLING 2021)
ACL