@inproceedings{mukherjee-etal-2022-ectsum,
title = "{ECTS}um: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts",
author = "Mukherjee, Rajdeep and
Bohra, Abhinav and
Banerjee, Akash and
Sharma, Soumya and
Hegde, Manjunath and
Shaikh, Afreen and
Shrivastava, Shivani and
Dasgupta, Koustuv and
Ganguly, Niloy and
Ghosh, Saptarshi and
Goyal, Pawan",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.748",
doi = "10.18653/v1/2022.emnlp-main.748",
pages = "10893--10906",
abstract = "Despite tremendous progress in automatic summarization, state-of-the-art methods are predominantly trained to excel in summarizing short newswire articles, or documents with strong layout biases such as scientific articles or government reports. Efficient techniques to summarize financial documents, discussing facts and figures, have largely been unexplored, majorly due to the unavailability of suitable datasets. In this work, we present ECTSum, a new dataset with transcripts of earnings calls (ECTs), hosted by publicly traded companies, as documents, and experts-written short telegram-style bullet point summaries derived from corresponding Reuters articles. ECTs are long unstructured documents without any prescribed length limit or format. We benchmark our dataset with state-of-the-art summarization methods across various metrics evaluating the content quality and factual consistency of the generated summaries. Finally, we present a simple yet effective approach, ECT-BPS, to generate a set of bullet points that precisely capture the important facts discussed in the calls.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mukherjee-etal-2022-ectsum">
<titleInfo>
<title>ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rajdeep</namePart>
<namePart type="family">Mukherjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Bohra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akash</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soumya</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manjunath</namePart>
<namePart type="family">Hegde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afreen</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shivani</namePart>
<namePart type="family">Shrivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koustuv</namePart>
<namePart type="family">Dasgupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niloy</namePart>
<namePart type="family">Ganguly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saptarshi</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite tremendous progress in automatic summarization, state-of-the-art methods are predominantly trained to excel in summarizing short newswire articles, or documents with strong layout biases such as scientific articles or government reports. Efficient techniques to summarize financial documents, discussing facts and figures, have largely been unexplored, majorly due to the unavailability of suitable datasets. In this work, we present ECTSum, a new dataset with transcripts of earnings calls (ECTs), hosted by publicly traded companies, as documents, and experts-written short telegram-style bullet point summaries derived from corresponding Reuters articles. ECTs are long unstructured documents without any prescribed length limit or format. We benchmark our dataset with state-of-the-art summarization methods across various metrics evaluating the content quality and factual consistency of the generated summaries. Finally, we present a simple yet effective approach, ECT-BPS, to generate a set of bullet points that precisely capture the important facts discussed in the calls.</abstract>
<identifier type="citekey">mukherjee-etal-2022-ectsum</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.748</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.748</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>10893</start>
<end>10906</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts
%A Mukherjee, Rajdeep
%A Bohra, Abhinav
%A Banerjee, Akash
%A Sharma, Soumya
%A Hegde, Manjunath
%A Shaikh, Afreen
%A Shrivastava, Shivani
%A Dasgupta, Koustuv
%A Ganguly, Niloy
%A Ghosh, Saptarshi
%A Goyal, Pawan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F mukherjee-etal-2022-ectsum
%X Despite tremendous progress in automatic summarization, state-of-the-art methods are predominantly trained to excel in summarizing short newswire articles, or documents with strong layout biases such as scientific articles or government reports. Efficient techniques to summarize financial documents, discussing facts and figures, have largely been unexplored, majorly due to the unavailability of suitable datasets. In this work, we present ECTSum, a new dataset with transcripts of earnings calls (ECTs), hosted by publicly traded companies, as documents, and experts-written short telegram-style bullet point summaries derived from corresponding Reuters articles. ECTs are long unstructured documents without any prescribed length limit or format. We benchmark our dataset with state-of-the-art summarization methods across various metrics evaluating the content quality and factual consistency of the generated summaries. Finally, we present a simple yet effective approach, ECT-BPS, to generate a set of bullet points that precisely capture the important facts discussed in the calls.
%R 10.18653/v1/2022.emnlp-main.748
%U https://aclanthology.org/2022.emnlp-main.748
%U https://doi.org/10.18653/v1/2022.emnlp-main.748
%P 10893-10906
Markdown (Informal)
[ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts](https://aclanthology.org/2022.emnlp-main.748) (Mukherjee et al., EMNLP 2022)
ACL
- Rajdeep Mukherjee, Abhinav Bohra, Akash Banerjee, Soumya Sharma, Manjunath Hegde, Afreen Shaikh, Shivani Shrivastava, Koustuv Dasgupta, Niloy Ganguly, Saptarshi Ghosh, and Pawan Goyal. 2022. ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10893–10906, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.