@inproceedings{magooda-etal-2021-exploring-multitask,
title = "Exploring Multitask Learning for Low-Resource Abstractive Summarization",
author = "Magooda, Ahmed and
Litman, Diane and
Elaraby, Mohamed",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.142",
doi = "10.18653/v1/2021.findings-emnlp.142",
pages = "1652--1661",
abstract = "This paper explores the effect of using multitask learning for abstractive summarization in the context of small training corpora. In particular, we incorporate four different tasks (extractive summarization, language modeling, concept detection, and paraphrase detection) both individually and in combination, with the goal of enhancing the target task of abstractive summarization via multitask learning. We show that for many task combinations, a model trained in a multitask setting outperforms a model trained only for abstractive summarization, with no additional summarization data introduced. Additionally, we do a comprehensive search and find that certain tasks (e.g. paraphrase detection) consistently benefit abstractive summarization, not only when combined with other tasks but also when using different architectures and training corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="magooda-etal-2021-exploring-multitask">
<titleInfo>
<title>Exploring Multitask Learning for Low-Resource Abstractive Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Magooda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diane</namePart>
<namePart type="family">Litman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Elaraby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper explores the effect of using multitask learning for abstractive summarization in the context of small training corpora. In particular, we incorporate four different tasks (extractive summarization, language modeling, concept detection, and paraphrase detection) both individually and in combination, with the goal of enhancing the target task of abstractive summarization via multitask learning. We show that for many task combinations, a model trained in a multitask setting outperforms a model trained only for abstractive summarization, with no additional summarization data introduced. Additionally, we do a comprehensive search and find that certain tasks (e.g. paraphrase detection) consistently benefit abstractive summarization, not only when combined with other tasks but also when using different architectures and training corpora.</abstract>
<identifier type="citekey">magooda-etal-2021-exploring-multitask</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.142</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.142</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>1652</start>
<end>1661</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Multitask Learning for Low-Resource Abstractive Summarization
%A Magooda, Ahmed
%A Litman, Diane
%A Elaraby, Mohamed
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F magooda-etal-2021-exploring-multitask
%X This paper explores the effect of using multitask learning for abstractive summarization in the context of small training corpora. In particular, we incorporate four different tasks (extractive summarization, language modeling, concept detection, and paraphrase detection) both individually and in combination, with the goal of enhancing the target task of abstractive summarization via multitask learning. We show that for many task combinations, a model trained in a multitask setting outperforms a model trained only for abstractive summarization, with no additional summarization data introduced. Additionally, we do a comprehensive search and find that certain tasks (e.g. paraphrase detection) consistently benefit abstractive summarization, not only when combined with other tasks but also when using different architectures and training corpora.
%R 10.18653/v1/2021.findings-emnlp.142
%U https://aclanthology.org/2021.findings-emnlp.142
%U https://doi.org/10.18653/v1/2021.findings-emnlp.142
%P 1652-1661
Markdown (Informal)
[Exploring Multitask Learning for Low-Resource Abstractive Summarization](https://aclanthology.org/2021.findings-emnlp.142) (Magooda et al., Findings 2021)
ACL