<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2020-find">
    <titleInfo>
        <title>Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jianguo</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kazuma</namePart>
        <namePart type="family">Hashimoto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chien-Sheng</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yao</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Philip</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Richard</namePart>
        <namePart type="family">Socher</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Caiming</namePart>
        <namePart type="family">Xiong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-dec</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Dialog state tracking (DST) is a core component in task-oriented dialog systems. Existing approaches for DST mainly fall into one of two categories, namely, ontology-based and ontology-free methods. An ontology-based method selects a value from a candidate-value list for each target slot, while an ontology-free method extracts spans from dialog contexts. Recent work introduced a BERT-based model to strike a balance between the two methods by pre-defining categorical and non-categorical slots. However, it is not clear enough which slots are better handled by either of the two slot types, and the way to use the pre-trained model has not been well investigated. In this paper, we propose a simple yet effective dual-strategy model for DST, by adapting a single BERT-style reading comprehension model to jointly handle both the categorical and non-categorical slots. Our experiments on the MultiWOZ datasets show that our method significantly outperforms the BERT-based counterpart, finding that the key is a deep interaction between the domain-slot and context information. When evaluated on noisy (MultiWOZ 2.0) and cleaner (MultiWOZ 2.1) settings, our method performs competitively and robustly across the two different settings. Our method sets the new state of the art in the noisy setting, while performing more robustly than the best model in the cleaner setting. We also conduct a comprehensive error analysis on the dataset, including the effects of the dual strategy for each slot, to facilitate future research.</abstract>
    <identifier type="citekey">zhang-etal-2020-find</identifier>
    <location>
        <url>https://aclanthology.org/2020.starsem-1.17</url>
    </location>
    <part>
        <date>2020-dec</date>
        <extent unit="page">
            <start>154</start>
            <end>167</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking
%A Zhang, Jianguo
%A Hashimoto, Kazuma
%A Wu, Chien-Sheng
%A Wang, Yao
%A Yu, Philip
%A Socher, Richard
%A Xiong, Caiming
%S Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics
%D 2020
%8 dec
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F zhang-etal-2020-find
%X Dialog state tracking (DST) is a core component in task-oriented dialog systems. Existing approaches for DST mainly fall into one of two categories, namely, ontology-based and ontology-free methods. An ontology-based method selects a value from a candidate-value list for each target slot, while an ontology-free method extracts spans from dialog contexts. Recent work introduced a BERT-based model to strike a balance between the two methods by pre-defining categorical and non-categorical slots. However, it is not clear enough which slots are better handled by either of the two slot types, and the way to use the pre-trained model has not been well investigated. In this paper, we propose a simple yet effective dual-strategy model for DST, by adapting a single BERT-style reading comprehension model to jointly handle both the categorical and non-categorical slots. Our experiments on the MultiWOZ datasets show that our method significantly outperforms the BERT-based counterpart, finding that the key is a deep interaction between the domain-slot and context information. When evaluated on noisy (MultiWOZ 2.0) and cleaner (MultiWOZ 2.1) settings, our method performs competitively and robustly across the two different settings. Our method sets the new state of the art in the noisy setting, while performing more robustly than the best model in the cleaner setting. We also conduct a comprehensive error analysis on the dataset, including the effects of the dual strategy for each slot, to facilitate future research.
%U https://aclanthology.org/2020.starsem-1.17
%P 154-167

Markdown (Informal)

[Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking](https://aclanthology.org/2020.starsem-1.17) (Zhang et al., *SEM 2020)

• Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking (Zhang et al., *SEM 2020)

ACL

• Jianguo Zhang, Kazuma Hashimoto, Chien-Sheng Wu, Yao Wang, Philip Yu, Richard Socher, and Caiming Xiong. 2020. Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking. In Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics, pages 154–167, Barcelona, Spain (Online). Association for Computational Linguistics.