@inproceedings{jiang-etal-2022-sehy,
title = "{SEHY}: A Simple yet Effective Hybrid Model for Summarization of Long Scientific Documents",
author = "Jiang, Zhihua and
Yang, Junzhan and
Rao, Dongning",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-aacl.9",
pages = "96--106",
abstract = "Long document (e.g., scientific papers) summarization is obtaining more and more attention in recent years. Extractive approaches attempt to choose salient sentences via understanding the whole document, but long documents cover numerous subjects with varying details and will not ease content understanding. Instead, abstractive approaches elaborate to generate related tokens while suffering from truncating the source document due to their input sizes. To this end, we propose a Simple yet Effective HYbrid approach, which we call SEHY, that exploits the discourse information of a document to select salient sections instead sentences for summary generation. On the one hand, SEHY avoids the full-text understanding; on the other hand, it retains salient information given the length limit. In particular, we design two simple strategies for training the extractor: extracting sections incrementally and based on salience-analysis. Then, we use strong abstractive models to generate the final summary. We evaluate our approach on a large-scale scientific paper dataset: arXiv. Further, we discuss how the disciplinary class (e.g., computer science, math or physics) of a scientific paper affects the performance of SEHY as its writing style indicates, which is unexplored yet in existing works. Experimental results show the effectiveness of our approach and interesting findings on arXiv and its subsets generated in this paper.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2022-sehy">
<titleInfo>
<title>SEHY: A Simple yet Effective Hybrid Model for Summarization of Long Scientific Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhihua</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junzhan</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongning</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</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">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Long document (e.g., scientific papers) summarization is obtaining more and more attention in recent years. Extractive approaches attempt to choose salient sentences via understanding the whole document, but long documents cover numerous subjects with varying details and will not ease content understanding. Instead, abstractive approaches elaborate to generate related tokens while suffering from truncating the source document due to their input sizes. To this end, we propose a Simple yet Effective HYbrid approach, which we call SEHY, that exploits the discourse information of a document to select salient sections instead sentences for summary generation. On the one hand, SEHY avoids the full-text understanding; on the other hand, it retains salient information given the length limit. In particular, we design two simple strategies for training the extractor: extracting sections incrementally and based on salience-analysis. Then, we use strong abstractive models to generate the final summary. We evaluate our approach on a large-scale scientific paper dataset: arXiv. Further, we discuss how the disciplinary class (e.g., computer science, math or physics) of a scientific paper affects the performance of SEHY as its writing style indicates, which is unexplored yet in existing works. Experimental results show the effectiveness of our approach and interesting findings on arXiv and its subsets generated in this paper.</abstract>
<identifier type="citekey">jiang-etal-2022-sehy</identifier>
<location>
<url>https://aclanthology.org/2022.findings-aacl.9</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>96</start>
<end>106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SEHY: A Simple yet Effective Hybrid Model for Summarization of Long Scientific Documents
%A Jiang, Zhihua
%A Yang, Junzhan
%A Rao, Dongning
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F jiang-etal-2022-sehy
%X Long document (e.g., scientific papers) summarization is obtaining more and more attention in recent years. Extractive approaches attempt to choose salient sentences via understanding the whole document, but long documents cover numerous subjects with varying details and will not ease content understanding. Instead, abstractive approaches elaborate to generate related tokens while suffering from truncating the source document due to their input sizes. To this end, we propose a Simple yet Effective HYbrid approach, which we call SEHY, that exploits the discourse information of a document to select salient sections instead sentences for summary generation. On the one hand, SEHY avoids the full-text understanding; on the other hand, it retains salient information given the length limit. In particular, we design two simple strategies for training the extractor: extracting sections incrementally and based on salience-analysis. Then, we use strong abstractive models to generate the final summary. We evaluate our approach on a large-scale scientific paper dataset: arXiv. Further, we discuss how the disciplinary class (e.g., computer science, math or physics) of a scientific paper affects the performance of SEHY as its writing style indicates, which is unexplored yet in existing works. Experimental results show the effectiveness of our approach and interesting findings on arXiv and its subsets generated in this paper.
%U https://aclanthology.org/2022.findings-aacl.9
%P 96-106
Markdown (Informal)
[SEHY: A Simple yet Effective Hybrid Model for Summarization of Long Scientific Documents](https://aclanthology.org/2022.findings-aacl.9) (Jiang et al., Findings 2022)
ACL