<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khalman-etal-2021-forumsum-multi">
    <titleInfo>
        <title>ForumSum: A Multi-Speaker Conversation Summarization Dataset</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Misha</namePart>
        <namePart type="family">Khalman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yao</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohammad</namePart>
        <namePart type="family">Saleh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <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>Abstractive summarization quality had large improvements since recent language pretraining techniques. However, currently there is a lack of datasets for the growing needs of conversation summarization applications. Thus we collected ForumSum, a diverse and high-quality conversation summarization dataset with human written summaries. The conversations in ForumSum dataset are collected from a wide variety of internet forums. To make the dataset easily expandable, we also release the process of dataset creation. Our experiments show that models trained on ForumSum have better zero-shot and few-shot transferability to other datasets than the existing large chat summarization dataset SAMSum. We also show that using a conversational corpus for pre-training improves the quality of the chat summarization model.</abstract>
    <identifier type="citekey">khalman-etal-2021-forumsum-multi</identifier>
    <identifier type="doi">10.18653/v1/2021.findings-emnlp.391</identifier>
    <location>
        <url>https://aclanthology.org/2021.findings-emnlp.391</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>4592</start>
            <end>4599</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ForumSum: A Multi-Speaker Conversation Summarization Dataset
%A Khalman, Misha
%A Zhao, Yao
%A Saleh, Mohammad
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F khalman-etal-2021-forumsum-multi
%X Abstractive summarization quality had large improvements since recent language pretraining techniques. However, currently there is a lack of datasets for the growing needs of conversation summarization applications. Thus we collected ForumSum, a diverse and high-quality conversation summarization dataset with human written summaries. The conversations in ForumSum dataset are collected from a wide variety of internet forums. To make the dataset easily expandable, we also release the process of dataset creation. Our experiments show that models trained on ForumSum have better zero-shot and few-shot transferability to other datasets than the existing large chat summarization dataset SAMSum. We also show that using a conversational corpus for pre-training improves the quality of the chat summarization model.
%R 10.18653/v1/2021.findings-emnlp.391
%U https://aclanthology.org/2021.findings-emnlp.391
%U https://doi.org/10.18653/v1/2021.findings-emnlp.391
%P 4592-4599

Markdown (Informal)

[ForumSum: A Multi-Speaker Conversation Summarization Dataset](https://aclanthology.org/2021.findings-emnlp.391) (Khalman et al., Findings 2021)

• ForumSum: A Multi-Speaker Conversation Summarization Dataset (Khalman et al., Findings 2021)

ACL

• Misha Khalman, Yao Zhao, and Mohammad Saleh. 2021. ForumSum: A Multi-Speaker Conversation Summarization Dataset. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4592–4599, Punta Cana, Dominican Republic. Association for Computational Linguistics.