<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hua-etal-2022-amrtvsumm">
    <titleInfo>
        <title>AMRTVSumm: AMR-augmented Hierarchical Network for TV Transcript Summarization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yilun</namePart>
        <namePart type="family">Hua</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhaoyuan</namePart>
        <namePart type="family">Deng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhijie</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Workshop on Automatic Summarization for Creative Writing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kathleen</namePart>
            <namePart type="family">Mckeown</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper describes our AMRTVSumm system for the SummScreen datasets in the Automatic Summarization for Creative Writing shared task (Creative-Summ 2022). In order to capture the complicated entity interactions and dialogue structures in transcripts of TV series, we introduce a new Abstract Meaning Representation (AMR) (Banarescu et al., 2013), particularly designed to represent individual scenes in an episode. We also propose a new cross-level cross-attention mechanism to incorporate these scene AMRs into a hierarchical encoder-decoder baseline. On both the ForeverDreaming and TVMegaSite datasets of SummScreen, our system consistently outperforms the hierarchical transformer baseline. Compared with the state-of-the-art DialogLM (Zhong et al., 2021), our system still has a lower performance primarily because it is pretrained only on out-of-domain news data, unlike DialogLM, which uses extensive in-domain pretraining on dialogue and TV show data. Overall, our work suggests a promising direction to capture complicated long dialogue structures through graph representations and the need to combine graph representations with powerful pretrained language models.</abstract>
    <identifier type="citekey">hua-etal-2022-amrtvsumm</identifier>
    <location>
        <url>https://aclanthology.org/2022.creativesumm-1.6/</url>
    </location>
    <part>
        <date>2022-10</date>
        <extent unit="page">
            <start>36</start>
            <end>43</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T AMRTVSumm: AMR-augmented Hierarchical Network for TV Transcript Summarization
%A Hua, Yilun
%A Deng, Zhaoyuan
%A Xu, Zhijie
%Y Mckeown, Kathleen
%S Proceedings of the Workshop on Automatic Summarization for Creative Writing
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F hua-etal-2022-amrtvsumm
%X This paper describes our AMRTVSumm system for the SummScreen datasets in the Automatic Summarization for Creative Writing shared task (Creative-Summ 2022). In order to capture the complicated entity interactions and dialogue structures in transcripts of TV series, we introduce a new Abstract Meaning Representation (AMR) (Banarescu et al., 2013), particularly designed to represent individual scenes in an episode. We also propose a new cross-level cross-attention mechanism to incorporate these scene AMRs into a hierarchical encoder-decoder baseline. On both the ForeverDreaming and TVMegaSite datasets of SummScreen, our system consistently outperforms the hierarchical transformer baseline. Compared with the state-of-the-art DialogLM (Zhong et al., 2021), our system still has a lower performance primarily because it is pretrained only on out-of-domain news data, unlike DialogLM, which uses extensive in-domain pretraining on dialogue and TV show data. Overall, our work suggests a promising direction to capture complicated long dialogue structures through graph representations and the need to combine graph representations with powerful pretrained language models.
%U https://aclanthology.org/2022.creativesumm-1.6/
%P 36-43

Markdown (Informal)

[AMRTVSumm: AMR-augmented Hierarchical Network for TV Transcript Summarization](https://aclanthology.org/2022.creativesumm-1.6/) (Hua et al., CreativeSumm 2022)

• AMRTVSumm: AMR-augmented Hierarchical Network for TV Transcript Summarization (Hua et al., CreativeSumm 2022)

ACL

• Yilun Hua, Zhaoyuan Deng, and Zhijie Xu. 2022. AMRTVSumm: AMR-augmented Hierarchical Network for TV Transcript Summarization. In Proceedings of the Workshop on Automatic Summarization for Creative Writing, pages 36–43, Gyeongju, Republic of Korea. Association for Computational Linguistics.