@inproceedings{qi-etal-2022-sapgraph,
title = "{SAPG}raph: Structure-aware Extractive Summarization for Scientific Papers with Heterogeneous Graph",
author = "Qi, Siya and
Li, Lei and
Li, Yiyang and
Jiang, Jin and
Hu, Dingxin and
Li, Yuze and
Zhu, Yingqi and
Zhou, Yanquan and
Litvak, Marina and
Vanetik, Natalia",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-main.44/",
doi = "10.18653/v1/2022.aacl-main.44",
pages = "575--586",
abstract = "Scientific paper summarization is always challenging in Natural Language Processing (NLP) since it is hard to collect summaries from such long and complicated text. We observe that previous works tend to extract summaries from the head of the paper, resulting in information incompleteness. In this work, we present SAPGraph to utilize paper structure for solving this problem. SAPGraph is a scientific paper extractive summarization framework based on a structure-aware heterogeneous graph, which models the document into a graph with three kinds of nodes and edges based on structure information of facets and knowledge. Additionally, we provide a large-scale dataset of COVID-19-related papers, CORD-SUM. Experiments on CORD-SUM and ArXiv datasets show that SAPGraph generates more comprehensive and valuable summaries compared to previous works."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qi-etal-2022-sapgraph">
<titleInfo>
<title>SAPGraph: Structure-aware Extractive Summarization for Scientific Papers with Heterogeneous Graph</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siya</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiyang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dingxin</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuze</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingqi</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanquan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Litvak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Vanetik</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>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</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>Scientific paper summarization is always challenging in Natural Language Processing (NLP) since it is hard to collect summaries from such long and complicated text. We observe that previous works tend to extract summaries from the head of the paper, resulting in information incompleteness. In this work, we present SAPGraph to utilize paper structure for solving this problem. SAPGraph is a scientific paper extractive summarization framework based on a structure-aware heterogeneous graph, which models the document into a graph with three kinds of nodes and edges based on structure information of facets and knowledge. Additionally, we provide a large-scale dataset of COVID-19-related papers, CORD-SUM. Experiments on CORD-SUM and ArXiv datasets show that SAPGraph generates more comprehensive and valuable summaries compared to previous works.</abstract>
<identifier type="citekey">qi-etal-2022-sapgraph</identifier>
<identifier type="doi">10.18653/v1/2022.aacl-main.44</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-main.44/</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>575</start>
<end>586</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SAPGraph: Structure-aware Extractive Summarization for Scientific Papers with Heterogeneous Graph
%A Qi, Siya
%A Li, Lei
%A Li, Yiyang
%A Jiang, Jin
%A Hu, Dingxin
%A Li, Yuze
%A Zhu, Yingqi
%A Zhou, Yanquan
%A Litvak, Marina
%A Vanetik, Natalia
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F qi-etal-2022-sapgraph
%X Scientific paper summarization is always challenging in Natural Language Processing (NLP) since it is hard to collect summaries from such long and complicated text. We observe that previous works tend to extract summaries from the head of the paper, resulting in information incompleteness. In this work, we present SAPGraph to utilize paper structure for solving this problem. SAPGraph is a scientific paper extractive summarization framework based on a structure-aware heterogeneous graph, which models the document into a graph with three kinds of nodes and edges based on structure information of facets and knowledge. Additionally, we provide a large-scale dataset of COVID-19-related papers, CORD-SUM. Experiments on CORD-SUM and ArXiv datasets show that SAPGraph generates more comprehensive and valuable summaries compared to previous works.
%R 10.18653/v1/2022.aacl-main.44
%U https://aclanthology.org/2022.aacl-main.44/
%U https://doi.org/10.18653/v1/2022.aacl-main.44
%P 575-586
Markdown (Informal)
[SAPGraph: Structure-aware Extractive Summarization for Scientific Papers with Heterogeneous Graph](https://aclanthology.org/2022.aacl-main.44/) (Qi et al., AACL-IJCNLP 2022)
ACL
- Siya Qi, Lei Li, Yiyang Li, Jin Jiang, Dingxin Hu, Yuze Li, Yingqi Zhu, Yanquan Zhou, Marina Litvak, and Natalia Vanetik. 2022. SAPGraph: Structure-aware Extractive Summarization for Scientific Papers with Heterogeneous Graph. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 575–586, Online only. Association for Computational Linguistics.