@inproceedings{gupta-etal-2021-sumpubmed,
title = "{SumPubMed}: Summarization Dataset of {P}ub{M}ed Scientific Articles",
author = "Gupta, Vivek and
Bharti, Prerna and
Nokhiz, Pegah and
Karnick, Harish",
editor = "Kabbara, Jad and
Lin, Haitao and
Paullada, Amandalynne and
Vamvas, Jannis",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-srw.30",
doi = "10.18653/v1/2021.acl-srw.30",
pages = "292--303",
abstract = "Most earlier work on text summarization is carried out on news article datasets. The summary in these datasets is naturally located at the beginning of the text. Hence, a model can spuriously utilize this correlation for summary generation instead of truly learning to summarize. To address this issue, we constructed a new dataset, SumPubMed , using scientific articles from the PubMed archive. We conducted a human analysis of summary coverage, redundancy, readability, coherence, and informativeness on SumPubMed . SumPubMed is challenging because (a) the summary is distributed throughout the text (not-localized on top), and (b) it contains rare domain-specific scientific terms. We observe that seq2seq models that adequately summarize news articles struggle to summarize SumPubMed . Thus, SumPubMed opens new avenues for the future improvement of models as well as the development of new evaluation metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2021-sumpubmed">
<titleInfo>
<title>SumPubMed: Summarization Dataset of PubMed Scientific Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prerna</namePart>
<namePart type="family">Bharti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pegah</namePart>
<namePart type="family">Nokhiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Karnick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jad</namePart>
<namePart type="family">Kabbara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haitao</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amandalynne</namePart>
<namePart type="family">Paullada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jannis</namePart>
<namePart type="family">Vamvas</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>Most earlier work on text summarization is carried out on news article datasets. The summary in these datasets is naturally located at the beginning of the text. Hence, a model can spuriously utilize this correlation for summary generation instead of truly learning to summarize. To address this issue, we constructed a new dataset, SumPubMed , using scientific articles from the PubMed archive. We conducted a human analysis of summary coverage, redundancy, readability, coherence, and informativeness on SumPubMed . SumPubMed is challenging because (a) the summary is distributed throughout the text (not-localized on top), and (b) it contains rare domain-specific scientific terms. We observe that seq2seq models that adequately summarize news articles struggle to summarize SumPubMed . Thus, SumPubMed opens new avenues for the future improvement of models as well as the development of new evaluation metrics.</abstract>
<identifier type="citekey">gupta-etal-2021-sumpubmed</identifier>
<identifier type="doi">10.18653/v1/2021.acl-srw.30</identifier>
<location>
<url>https://aclanthology.org/2021.acl-srw.30</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>292</start>
<end>303</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SumPubMed: Summarization Dataset of PubMed Scientific Articles
%A Gupta, Vivek
%A Bharti, Prerna
%A Nokhiz, Pegah
%A Karnick, Harish
%Y Kabbara, Jad
%Y Lin, Haitao
%Y Paullada, Amandalynne
%Y Vamvas, Jannis
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F gupta-etal-2021-sumpubmed
%X Most earlier work on text summarization is carried out on news article datasets. The summary in these datasets is naturally located at the beginning of the text. Hence, a model can spuriously utilize this correlation for summary generation instead of truly learning to summarize. To address this issue, we constructed a new dataset, SumPubMed , using scientific articles from the PubMed archive. We conducted a human analysis of summary coverage, redundancy, readability, coherence, and informativeness on SumPubMed . SumPubMed is challenging because (a) the summary is distributed throughout the text (not-localized on top), and (b) it contains rare domain-specific scientific terms. We observe that seq2seq models that adequately summarize news articles struggle to summarize SumPubMed . Thus, SumPubMed opens new avenues for the future improvement of models as well as the development of new evaluation metrics.
%R 10.18653/v1/2021.acl-srw.30
%U https://aclanthology.org/2021.acl-srw.30
%U https://doi.org/10.18653/v1/2021.acl-srw.30
%P 292-303
Markdown (Informal)
[SumPubMed: Summarization Dataset of PubMed Scientific Articles](https://aclanthology.org/2021.acl-srw.30) (Gupta et al., ACL-IJCNLP 2021)
ACL
- Vivek Gupta, Prerna Bharti, Pegah Nokhiz, and Harish Karnick. 2021. SumPubMed: Summarization Dataset of PubMed Scientific Articles. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop, pages 292–303, Online. Association for Computational Linguistics.