@inproceedings{phan-etal-2022-hetergraphlongsum,
title = "{H}eter{G}raph{L}ong{S}um: Heterogeneous Graph Neural Network with Passage Aggregation for Extractive Long Document Summarization",
author = "Phan, Tuan-Anh and
Nguyen, Ngoc-Dung Ngoc and
Bui, Khac-Hoai Nam",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.545",
pages = "6248--6258",
abstract = "Graph Neural Network (GNN)-based models have proven effective in various Natural Language Processing (NLP) tasks in recent years. Specifically, in the case of the Extractive Document Summarization (EDS) task, modeling documents under graph structure is able to analyze the complex relations between semantic units (e.g., word-to-word, word-to-sentence, sentence-to-sentence) and enrich sentence representations via valuable information from their neighbors. However, long-form document summarization using graph-based methods is still an open research issue. The main challenge is to represent long documents in a graph structure in an effective way. In this regard, this paper proposes a new heterogeneous graph neural network (HeterGNN) model to improve the performance of long document summarization (HeterGraphLongSum). Specifically, the main idea is to add the passage nodes into the heterogeneous graph structure of word and sentence nodes for enriching the final representation of sentences. In this regard, HeterGraphLongSum is designed with three types of semantic units such as word, sentence, and passage. Experiments on two benchmark datasets for long documents such as Pubmed and Arxiv indicate promising results of the proposed model for the extractive long document summarization problem. Especially, HeterGraphLongSum is able to achieve state-of-the-art performance without relying on any pre-trained language models (e.g., BERT). The source code is available for further exploitation on the Github.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="phan-etal-2022-hetergraphlongsum">
<titleInfo>
<title>HeterGraphLongSum: Heterogeneous Graph Neural Network with Passage Aggregation for Extractive Long Document Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tuan-Anh</namePart>
<namePart type="family">Phan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngoc-Dung</namePart>
<namePart type="given">Ngoc</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khac-Hoai</namePart>
<namePart type="given">Nam</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Graph Neural Network (GNN)-based models have proven effective in various Natural Language Processing (NLP) tasks in recent years. Specifically, in the case of the Extractive Document Summarization (EDS) task, modeling documents under graph structure is able to analyze the complex relations between semantic units (e.g., word-to-word, word-to-sentence, sentence-to-sentence) and enrich sentence representations via valuable information from their neighbors. However, long-form document summarization using graph-based methods is still an open research issue. The main challenge is to represent long documents in a graph structure in an effective way. In this regard, this paper proposes a new heterogeneous graph neural network (HeterGNN) model to improve the performance of long document summarization (HeterGraphLongSum). Specifically, the main idea is to add the passage nodes into the heterogeneous graph structure of word and sentence nodes for enriching the final representation of sentences. In this regard, HeterGraphLongSum is designed with three types of semantic units such as word, sentence, and passage. Experiments on two benchmark datasets for long documents such as Pubmed and Arxiv indicate promising results of the proposed model for the extractive long document summarization problem. Especially, HeterGraphLongSum is able to achieve state-of-the-art performance without relying on any pre-trained language models (e.g., BERT). The source code is available for further exploitation on the Github.</abstract>
<identifier type="citekey">phan-etal-2022-hetergraphlongsum</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.545</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>6248</start>
<end>6258</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HeterGraphLongSum: Heterogeneous Graph Neural Network with Passage Aggregation for Extractive Long Document Summarization
%A Phan, Tuan-Anh
%A Nguyen, Ngoc-Dung Ngoc
%A Bui, Khac-Hoai Nam
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F phan-etal-2022-hetergraphlongsum
%X Graph Neural Network (GNN)-based models have proven effective in various Natural Language Processing (NLP) tasks in recent years. Specifically, in the case of the Extractive Document Summarization (EDS) task, modeling documents under graph structure is able to analyze the complex relations between semantic units (e.g., word-to-word, word-to-sentence, sentence-to-sentence) and enrich sentence representations via valuable information from their neighbors. However, long-form document summarization using graph-based methods is still an open research issue. The main challenge is to represent long documents in a graph structure in an effective way. In this regard, this paper proposes a new heterogeneous graph neural network (HeterGNN) model to improve the performance of long document summarization (HeterGraphLongSum). Specifically, the main idea is to add the passage nodes into the heterogeneous graph structure of word and sentence nodes for enriching the final representation of sentences. In this regard, HeterGraphLongSum is designed with three types of semantic units such as word, sentence, and passage. Experiments on two benchmark datasets for long documents such as Pubmed and Arxiv indicate promising results of the proposed model for the extractive long document summarization problem. Especially, HeterGraphLongSum is able to achieve state-of-the-art performance without relying on any pre-trained language models (e.g., BERT). The source code is available for further exploitation on the Github.
%U https://aclanthology.org/2022.coling-1.545
%P 6248-6258
Markdown (Informal)
[HeterGraphLongSum: Heterogeneous Graph Neural Network with Passage Aggregation for Extractive Long Document Summarization](https://aclanthology.org/2022.coling-1.545) (Phan et al., COLING 2022)
ACL