@inproceedings{srivastava-etal-2023-hiding,
title = "Hiding in Plain Sight: Insights into Abstractive Text Summarization",
author = "Srivastava, Vivek and
Bhat, Savita and
Pedanekar, Niranjan",
editor = "Tafreshi, Shabnam and
Akula, Arjun and
Sedoc, Jo{\~a}o and
Drozd, Aleksandr and
Rogers, Anna and
Rumshisky, Anna",
booktitle = "Proceedings of the Fourth Workshop on Insights from Negative Results in NLP",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.insights-1.8",
doi = "10.18653/v1/2023.insights-1.8",
pages = "67--74",
abstract = "In recent years, there has been growing interest in the field of abstractive text summarization with focused contributions in relevant model architectures, datasets, and evaluation metrics. Despite notable research advances, previous works have identified certain limitations concerning the quality of datasets and the effectiveness of evaluation techniques for generated summaries. In this context, we examine these limitations further with the help of three quality measures, namely, Information Coverage, Entity Hallucination, and Summarization Complexity. As a part of this work, we investigate two widely used datasets (XSUM and CNNDM) and three existing models (BART, PEGASUS, and BRIO) and report our findings. Some key insights are: 1) Cumulative ROUGE score is an inappropriate evaluation measure since few high-scoring samples dominate the overall performance, 2) Existing summarization models have limited capability for information coverage and hallucinate to generate factual information, and 3) Compared to the model generated summaries, the reference summaries have lowest information coverage and highest entity hallucinations reiterating the need of new and better reference summaries.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="srivastava-etal-2023-hiding">
<titleInfo>
<title>Hiding in Plain Sight: Insights into Abstractive Text Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Savita</namePart>
<namePart type="family">Bhat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niranjan</namePart>
<namePart type="family">Pedanekar</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 Fourth Workshop on Insights from Negative Results in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Akula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandr</namePart>
<namePart type="family">Drozd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</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 recent years, there has been growing interest in the field of abstractive text summarization with focused contributions in relevant model architectures, datasets, and evaluation metrics. Despite notable research advances, previous works have identified certain limitations concerning the quality of datasets and the effectiveness of evaluation techniques for generated summaries. In this context, we examine these limitations further with the help of three quality measures, namely, Information Coverage, Entity Hallucination, and Summarization Complexity. As a part of this work, we investigate two widely used datasets (XSUM and CNNDM) and three existing models (BART, PEGASUS, and BRIO) and report our findings. Some key insights are: 1) Cumulative ROUGE score is an inappropriate evaluation measure since few high-scoring samples dominate the overall performance, 2) Existing summarization models have limited capability for information coverage and hallucinate to generate factual information, and 3) Compared to the model generated summaries, the reference summaries have lowest information coverage and highest entity hallucinations reiterating the need of new and better reference summaries.</abstract>
<identifier type="citekey">srivastava-etal-2023-hiding</identifier>
<identifier type="doi">10.18653/v1/2023.insights-1.8</identifier>
<location>
<url>https://aclanthology.org/2023.insights-1.8</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>67</start>
<end>74</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hiding in Plain Sight: Insights into Abstractive Text Summarization
%A Srivastava, Vivek
%A Bhat, Savita
%A Pedanekar, Niranjan
%Y Tafreshi, Shabnam
%Y Akula, Arjun
%Y Sedoc, João
%Y Drozd, Aleksandr
%Y Rogers, Anna
%Y Rumshisky, Anna
%S Proceedings of the Fourth Workshop on Insights from Negative Results in NLP
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F srivastava-etal-2023-hiding
%X In recent years, there has been growing interest in the field of abstractive text summarization with focused contributions in relevant model architectures, datasets, and evaluation metrics. Despite notable research advances, previous works have identified certain limitations concerning the quality of datasets and the effectiveness of evaluation techniques for generated summaries. In this context, we examine these limitations further with the help of three quality measures, namely, Information Coverage, Entity Hallucination, and Summarization Complexity. As a part of this work, we investigate two widely used datasets (XSUM and CNNDM) and three existing models (BART, PEGASUS, and BRIO) and report our findings. Some key insights are: 1) Cumulative ROUGE score is an inappropriate evaluation measure since few high-scoring samples dominate the overall performance, 2) Existing summarization models have limited capability for information coverage and hallucinate to generate factual information, and 3) Compared to the model generated summaries, the reference summaries have lowest information coverage and highest entity hallucinations reiterating the need of new and better reference summaries.
%R 10.18653/v1/2023.insights-1.8
%U https://aclanthology.org/2023.insights-1.8
%U https://doi.org/10.18653/v1/2023.insights-1.8
%P 67-74
Markdown (Informal)
[Hiding in Plain Sight: Insights into Abstractive Text Summarization](https://aclanthology.org/2023.insights-1.8) (Srivastava et al., insights-WS 2023)
ACL