@inproceedings{lebanoff-etal-2020-learning,
title = "Learning to Fuse Sentences with Transformers for Summarization",
author = "Lebanoff, Logan and
Dernoncourt, Franck and
Kim, Doo Soon and
Wang, Lidan and
Chang, Walter and
Liu, Fei",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.338",
doi = "10.18653/v1/2020.emnlp-main.338",
pages = "4136--4142",
abstract = "The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts. However, to date, summarizers can fail on fusing sentences. They tend to produce few summary sentences by fusion or generate incorrect fusions that lead the summary to fail to retain the original meaning. In this paper, we explore the ability of Transformers to fuse sentences and propose novel algorithms to enhance their ability to perform sentence fusion by leveraging the knowledge of points of correspondence between sentences. Through extensive experiments, we investigate the effects of different design choices on Transformer{'}s performance. Our findings highlight the importance of modeling points of correspondence between sentences for effective sentence fusion.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lebanoff-etal-2020-learning">
<titleInfo>
<title>Learning to Fuse Sentences with Transformers for Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Logan</namePart>
<namePart type="family">Lebanoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doo</namePart>
<namePart type="given">Soon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walter</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts. However, to date, summarizers can fail on fusing sentences. They tend to produce few summary sentences by fusion or generate incorrect fusions that lead the summary to fail to retain the original meaning. In this paper, we explore the ability of Transformers to fuse sentences and propose novel algorithms to enhance their ability to perform sentence fusion by leveraging the knowledge of points of correspondence between sentences. Through extensive experiments, we investigate the effects of different design choices on Transformer’s performance. Our findings highlight the importance of modeling points of correspondence between sentences for effective sentence fusion.</abstract>
<identifier type="citekey">lebanoff-etal-2020-learning</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.338</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.338</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>4136</start>
<end>4142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Fuse Sentences with Transformers for Summarization
%A Lebanoff, Logan
%A Dernoncourt, Franck
%A Kim, Doo Soon
%A Wang, Lidan
%A Chang, Walter
%A Liu, Fei
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F lebanoff-etal-2020-learning
%X The ability to fuse sentences is highly attractive for summarization systems because it is an essential step to produce succinct abstracts. However, to date, summarizers can fail on fusing sentences. They tend to produce few summary sentences by fusion or generate incorrect fusions that lead the summary to fail to retain the original meaning. In this paper, we explore the ability of Transformers to fuse sentences and propose novel algorithms to enhance their ability to perform sentence fusion by leveraging the knowledge of points of correspondence between sentences. Through extensive experiments, we investigate the effects of different design choices on Transformer’s performance. Our findings highlight the importance of modeling points of correspondence between sentences for effective sentence fusion.
%R 10.18653/v1/2020.emnlp-main.338
%U https://aclanthology.org/2020.emnlp-main.338
%U https://doi.org/10.18653/v1/2020.emnlp-main.338
%P 4136-4142
Markdown (Informal)
[Learning to Fuse Sentences with Transformers for Summarization](https://aclanthology.org/2020.emnlp-main.338) (Lebanoff et al., EMNLP 2020)
ACL
- Logan Lebanoff, Franck Dernoncourt, Doo Soon Kim, Lidan Wang, Walter Chang, and Fei Liu. 2020. Learning to Fuse Sentences with Transformers for Summarization. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4136–4142, Online. Association for Computational Linguistics.