@inproceedings{sotudeh-gharebagh-etal-2020-guir,
title = "{GUIR} @ {L}ong{S}umm 2020: Learning to Generate Long Summaries from Scientific Documents",
author = "Sotudeh Gharebagh, Sajad and
Cohan, Arman and
Goharian, Nazli",
editor = "Chandrasekaran, Muthu Kumar and
de Waard, Anita and
Feigenblat, Guy and
Freitag, Dayne and
Ghosal, Tirthankar and
Hovy, Eduard and
Knoth, Petr and
Konopnicki, David and
Mayr, Philipp and
Patton, Robert M. and
Shmueli-Scheuer, Michal",
booktitle = "Proceedings of the First Workshop on Scholarly Document Processing",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sdp-1.41/",
doi = "10.18653/v1/2020.sdp-1.41",
pages = "356--361",
abstract = "This paper presents our methods for the LongSumm 2020: Shared Task on Generating Long Summaries for Scientific Documents, where the task is to generatelong summaries given a set of scientific papers provided by the organizers. We explore 3 main approaches for this task: 1. An extractive approach using a BERT-based summarization model; 2. A two stage model that additionally includes an abstraction step using BART; and 3. A new multi-tasking approach on incorporating document structure into the summarizer. We found that our new multi-tasking approach outperforms the two other methods by large margins. Among 9 participants in the shared task, our best model ranks top according to Rouge-1 score (53.11{\%}) while staying competitive in terms of Rouge-2."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sotudeh-gharebagh-etal-2020-guir">
<titleInfo>
<title>GUIR @ LongSumm 2020: Learning to Generate Long Summaries from Scientific Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sajad</namePart>
<namePart type="family">Sotudeh Gharebagh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arman</namePart>
<namePart type="family">Cohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazli</namePart>
<namePart type="family">Goharian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Scholarly Document Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muthu</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Chandrasekaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">de Waard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Feigenblat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayne</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Knoth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Konopnicki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Patton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Shmueli-Scheuer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our methods for the LongSumm 2020: Shared Task on Generating Long Summaries for Scientific Documents, where the task is to generatelong summaries given a set of scientific papers provided by the organizers. We explore 3 main approaches for this task: 1. An extractive approach using a BERT-based summarization model; 2. A two stage model that additionally includes an abstraction step using BART; and 3. A new multi-tasking approach on incorporating document structure into the summarizer. We found that our new multi-tasking approach outperforms the two other methods by large margins. Among 9 participants in the shared task, our best model ranks top according to Rouge-1 score (53.11%) while staying competitive in terms of Rouge-2.</abstract>
<identifier type="citekey">sotudeh-gharebagh-etal-2020-guir</identifier>
<identifier type="doi">10.18653/v1/2020.sdp-1.41</identifier>
<location>
<url>https://aclanthology.org/2020.sdp-1.41/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>356</start>
<end>361</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GUIR @ LongSumm 2020: Learning to Generate Long Summaries from Scientific Documents
%A Sotudeh Gharebagh, Sajad
%A Cohan, Arman
%A Goharian, Nazli
%Y Chandrasekaran, Muthu Kumar
%Y de Waard, Anita
%Y Feigenblat, Guy
%Y Freitag, Dayne
%Y Ghosal, Tirthankar
%Y Hovy, Eduard
%Y Knoth, Petr
%Y Konopnicki, David
%Y Mayr, Philipp
%Y Patton, Robert M.
%Y Shmueli-Scheuer, Michal
%S Proceedings of the First Workshop on Scholarly Document Processing
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F sotudeh-gharebagh-etal-2020-guir
%X This paper presents our methods for the LongSumm 2020: Shared Task on Generating Long Summaries for Scientific Documents, where the task is to generatelong summaries given a set of scientific papers provided by the organizers. We explore 3 main approaches for this task: 1. An extractive approach using a BERT-based summarization model; 2. A two stage model that additionally includes an abstraction step using BART; and 3. A new multi-tasking approach on incorporating document structure into the summarizer. We found that our new multi-tasking approach outperforms the two other methods by large margins. Among 9 participants in the shared task, our best model ranks top according to Rouge-1 score (53.11%) while staying competitive in terms of Rouge-2.
%R 10.18653/v1/2020.sdp-1.41
%U https://aclanthology.org/2020.sdp-1.41/
%U https://doi.org/10.18653/v1/2020.sdp-1.41
%P 356-361
Markdown (Informal)
[GUIR @ LongSumm 2020: Learning to Generate Long Summaries from Scientific Documents](https://aclanthology.org/2020.sdp-1.41/) (Sotudeh Gharebagh et al., sdp 2020)
ACL