<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2021-knowledge">
    <titleInfo>
        <title>Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Weizhe</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bo-Hsiang</namePart>
        <namePart type="family">Tseng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bill</namePart>
        <namePart type="family">Byrne</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>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</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">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances. We present a novel hybrid architecture that augments GPT-2 with representations derived from Graph Attention Networks in such a way to allow causal, sequential prediction of slot values. The model architecture captures inter-slot relationships and dependencies across domains that otherwise can be lost in sequential prediction. We report improvements in state tracking performance in MultiWOZ 2.0 against a strong GPT-2 baseline and investigate a simplified sparse training scenario in which DST models are trained only on session-level annotations but evaluated at the turn level. We further report detailed analyses to demonstrate the effectiveness of graph models in DST by showing that the proposed graph modules capture inter-slot dependencies and improve the predictions of values that are common to multiple domains.</abstract>
    <identifier type="citekey">lin-etal-2021-knowledge</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.620</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.620</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>7871</start>
            <end>7881</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking
%A Lin, Weizhe
%A Tseng, Bo-Hsiang
%A Byrne, Bill
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F lin-etal-2021-knowledge
%X Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances. We present a novel hybrid architecture that augments GPT-2 with representations derived from Graph Attention Networks in such a way to allow causal, sequential prediction of slot values. The model architecture captures inter-slot relationships and dependencies across domains that otherwise can be lost in sequential prediction. We report improvements in state tracking performance in MultiWOZ 2.0 against a strong GPT-2 baseline and investigate a simplified sparse training scenario in which DST models are trained only on session-level annotations but evaluated at the turn level. We further report detailed analyses to demonstrate the effectiveness of graph models in DST by showing that the proposed graph modules capture inter-slot dependencies and improve the predictions of values that are common to multiple domains.
%R 10.18653/v1/2021.emnlp-main.620
%U https://aclanthology.org/2021.emnlp-main.620
%U https://doi.org/10.18653/v1/2021.emnlp-main.620
%P 7871-7881

Markdown (Informal)

[Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking](https://aclanthology.org/2021.emnlp-main.620) (Lin et al., EMNLP 2021)

• Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking (Lin et al., EMNLP 2021)

ACL

• Weizhe Lin, Bo-Hsiang Tseng, and Bill Byrne. 2021. Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7871–7881, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.