<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uma-naresh-etal-2022-pentatron">
    <titleInfo>
        <title>PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Niranjan</namePart>
        <namePart type="family">Uma Naresh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ziyan</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ankit</namePart>
        <namePart type="family">Ankit</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sungjin</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jie</namePart>
        <namePart type="family">Hao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xing</namePart>
        <namePart type="family">Fan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chenlei</namePart>
        <namePart type="family">Guo</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: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yunyao</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Angeliki</namePart>
            <namePart type="family">Lazaridou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, UAE</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Conversational understanding is an integral part of modern intelligent devices. In a large fraction of the global traffic from customers using smart digital assistants, frictions in dialogues may be attributed to incorrect understanding of the entities in a customer’s query due to factors including ambiguous mentions, mispronunciation, background noise and faulty on-device signal processing. Such errors are compounded by two common deficiencies from intelligent devices namely, (1) the device not being tailored to individual customers, and (2) the device responses being unaware of the context in the conversation session. Viewing this problem via the lens of retrieval-based search engines, we build and evaluate a scalable entity correction system, PENTATRON. The system leverages a parametric transformer-based language model to learn patterns from in-session customer-device interactions coupled with a non-parametric personalized entity index to compute the correct query, which aids downstream components in reasoning about the best response. In addition to establishing baselines and demonstrating the value of personalized and context-aware systems, we use multitasking to learn the domain of the correct entity. We also investigate the utility of language model prompts. Through extensive experiments, we show a significant upward movement of the key metric (Exact Match) by up to 500.97% (relative to the baseline).</abstract>
    <identifier type="citekey">uma-naresh-etal-2022-pentatron</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-industry.7</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-industry.7</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>90</start>
            <end>98</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding
%A Uma Naresh, Niranjan
%A Jiang, Ziyan
%A Ankit, Ankit
%A Lee, Sungjin
%A Hao, Jie
%A Fan, Xing
%A Guo, Chenlei
%Y Li, Yunyao
%Y Lazaridou, Angeliki
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F uma-naresh-etal-2022-pentatron
%X Conversational understanding is an integral part of modern intelligent devices. In a large fraction of the global traffic from customers using smart digital assistants, frictions in dialogues may be attributed to incorrect understanding of the entities in a customer’s query due to factors including ambiguous mentions, mispronunciation, background noise and faulty on-device signal processing. Such errors are compounded by two common deficiencies from intelligent devices namely, (1) the device not being tailored to individual customers, and (2) the device responses being unaware of the context in the conversation session. Viewing this problem via the lens of retrieval-based search engines, we build and evaluate a scalable entity correction system, PENTATRON. The system leverages a parametric transformer-based language model to learn patterns from in-session customer-device interactions coupled with a non-parametric personalized entity index to compute the correct query, which aids downstream components in reasoning about the best response. In addition to establishing baselines and demonstrating the value of personalized and context-aware systems, we use multitasking to learn the domain of the correct entity. We also investigate the utility of language model prompts. Through extensive experiments, we show a significant upward movement of the key metric (Exact Match) by up to 500.97% (relative to the baseline).
%R 10.18653/v1/2022.emnlp-industry.7
%U https://aclanthology.org/2022.emnlp-industry.7
%U https://doi.org/10.18653/v1/2022.emnlp-industry.7
%P 90-98

Markdown (Informal)

[PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding](https://aclanthology.org/2022.emnlp-industry.7) (Uma Naresh et al., EMNLP 2022)

• PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding (Uma Naresh et al., EMNLP 2022)

ACL

• Niranjan Uma Naresh, Ziyan Jiang, Ankit Ankit, Sungjin Lee, Jie Hao, Xing Fan, and Chenlei Guo. 2022. PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 90–98, Abu Dhabi, UAE. Association for Computational Linguistics.