@inproceedings{deutsch-roth-2023-incorporating,
title = "Incorporating Question Answering-Based Signals into Abstractive Summarization via Salient Span Selection",
author = "Deutsch, Daniel and
Roth, Dan",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.42",
doi = "10.18653/v1/2023.eacl-main.42",
pages = "575--588",
abstract = "In this work, we propose a method for incorporating question-answering (QA) signals into a summarization model. Our method identifies salient noun phrases (NPs) in the input document by automatically generating wh-questions that are answered by the NPs and automatically determining whether those questions are answered in the gold summaries. This QA-based signal is incorporated into a two-stage summarization model which first marks salient NPs in the input document using a classification model, then conditionally generates a summary. Our experiments demonstrate that the models trained using QA-based supervision generate higher-quality summaries than baseline methods of identifying salient spans on benchmark summarization datasets. Further, we show that the content of the generated summaries can be controlled based on which NPs are marked in the input document. Finally, we propose a method of augmenting the training data so the gold summaries are more consistent with the marked input spans used during training and show how this results in models which learn to better exclude unmarked document content.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deutsch-roth-2023-incorporating">
<titleInfo>
<title>Incorporating Question Answering-Based Signals into Abstractive Summarization via Salient Span Selection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Deutsch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we propose a method for incorporating question-answering (QA) signals into a summarization model. Our method identifies salient noun phrases (NPs) in the input document by automatically generating wh-questions that are answered by the NPs and automatically determining whether those questions are answered in the gold summaries. This QA-based signal is incorporated into a two-stage summarization model which first marks salient NPs in the input document using a classification model, then conditionally generates a summary. Our experiments demonstrate that the models trained using QA-based supervision generate higher-quality summaries than baseline methods of identifying salient spans on benchmark summarization datasets. Further, we show that the content of the generated summaries can be controlled based on which NPs are marked in the input document. Finally, we propose a method of augmenting the training data so the gold summaries are more consistent with the marked input spans used during training and show how this results in models which learn to better exclude unmarked document content.</abstract>
<identifier type="citekey">deutsch-roth-2023-incorporating</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.42</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.42</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>575</start>
<end>588</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating Question Answering-Based Signals into Abstractive Summarization via Salient Span Selection
%A Deutsch, Daniel
%A Roth, Dan
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F deutsch-roth-2023-incorporating
%X In this work, we propose a method for incorporating question-answering (QA) signals into a summarization model. Our method identifies salient noun phrases (NPs) in the input document by automatically generating wh-questions that are answered by the NPs and automatically determining whether those questions are answered in the gold summaries. This QA-based signal is incorporated into a two-stage summarization model which first marks salient NPs in the input document using a classification model, then conditionally generates a summary. Our experiments demonstrate that the models trained using QA-based supervision generate higher-quality summaries than baseline methods of identifying salient spans on benchmark summarization datasets. Further, we show that the content of the generated summaries can be controlled based on which NPs are marked in the input document. Finally, we propose a method of augmenting the training data so the gold summaries are more consistent with the marked input spans used during training and show how this results in models which learn to better exclude unmarked document content.
%R 10.18653/v1/2023.eacl-main.42
%U https://aclanthology.org/2023.eacl-main.42
%U https://doi.org/10.18653/v1/2023.eacl-main.42
%P 575-588
Markdown (Informal)
[Incorporating Question Answering-Based Signals into Abstractive Summarization via Salient Span Selection](https://aclanthology.org/2023.eacl-main.42) (Deutsch & Roth, EACL 2023)
ACL