<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nathan-etal-2023-investigating">
    <titleInfo>
        <title>Investigating the Role and Impact of Disfluency on Summarization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Varun</namePart>
        <namePart type="family">Nathan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ayush</namePart>
        <namePart type="family">Kumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jithendra</namePart>
        <namePart type="family">Vepa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mingxuan</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Imed</namePart>
            <namePart type="family">Zitouni</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Contact centers handle both chat and voice calls for the same domain. As part of their workflow, it is a standard practice to summarize the conversations once they conclude. A significant distinction between chat and voice communication lies in the presence of disfluencies in voice calls, such as repetitions, restarts, and replacements. These disfluencies are generally considered noise for downstream natural language understanding (NLU) tasks. While a separate summarization model for voice calls can be trained in addition to chat specific model for the same domain, it requires manual annotations for both the channels and adds complexity arising due to maintaining two models. Therefore, it’s crucial to investigate if a model trained on fluent data can handle disfluent data effectively. While previous research explored impact of disfluency on question-answering and intent detection, its influence on summarization is inadequately studied. Our experiments reveal up to 6.99-point degradation in Rouge-L score, along with reduced fluency, consistency, and relevance when a fluent-trained model handles disfluent data. Replacement disfluencies have the highest negative impact. To mitigate this, we examine Fused-Fine Tuning by training the model with a combination of fluent and disfluent data, resulting in improved performance on both public and real-life datasets. Our work highlights the significance of incorporating disfluency in training summarization models and its advantages in an industrial setting.</abstract>
    <identifier type="citekey">nathan-etal-2023-investigating</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-industry.52</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-industry.52</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>541</start>
            <end>551</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Investigating the Role and Impact of Disfluency on Summarization
%A Nathan, Varun
%A Kumar, Ayush
%A Vepa, Jithendra
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F nathan-etal-2023-investigating
%X Contact centers handle both chat and voice calls for the same domain. As part of their workflow, it is a standard practice to summarize the conversations once they conclude. A significant distinction between chat and voice communication lies in the presence of disfluencies in voice calls, such as repetitions, restarts, and replacements. These disfluencies are generally considered noise for downstream natural language understanding (NLU) tasks. While a separate summarization model for voice calls can be trained in addition to chat specific model for the same domain, it requires manual annotations for both the channels and adds complexity arising due to maintaining two models. Therefore, it’s crucial to investigate if a model trained on fluent data can handle disfluent data effectively. While previous research explored impact of disfluency on question-answering and intent detection, its influence on summarization is inadequately studied. Our experiments reveal up to 6.99-point degradation in Rouge-L score, along with reduced fluency, consistency, and relevance when a fluent-trained model handles disfluent data. Replacement disfluencies have the highest negative impact. To mitigate this, we examine Fused-Fine Tuning by training the model with a combination of fluent and disfluent data, resulting in improved performance on both public and real-life datasets. Our work highlights the significance of incorporating disfluency in training summarization models and its advantages in an industrial setting.
%R 10.18653/v1/2023.emnlp-industry.52
%U https://aclanthology.org/2023.emnlp-industry.52
%U https://doi.org/10.18653/v1/2023.emnlp-industry.52
%P 541-551

Markdown (Informal)

[Investigating the Role and Impact of Disfluency on Summarization](https://aclanthology.org/2023.emnlp-industry.52) (Nathan et al., EMNLP 2023)

• Investigating the Role and Impact of Disfluency on Summarization (Nathan et al., EMNLP 2023)

ACL

• Varun Nathan, Ayush Kumar, and Jithendra Vepa. 2023. Investigating the Role and Impact of Disfluency on Summarization. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 541–551, Singapore. Association for Computational Linguistics.