@inproceedings{rastogi-etal-2019-scaling,
title = "Scaling Multi-Domain Dialogue State Tracking via Query Reformulation",
author = "Rastogi, Pushpendre and
Gupta, Arpit and
Chen, Tongfei and
Lambert, Mathias",
editor = "Loukina, Anastassia and
Morales, Michelle and
Kumar, Rohit",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-2013",
doi = "10.18653/v1/N19-2013",
pages = "97--105",
abstract = "We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the entities relevant to the conversation across turns. Tracking conversational state is particularly challenging in a multi-domain scenario when there exist multiple spoken language understanding (SLU) sub-systems, and each SLU sub-system operates on its domain-specific meaning representation. While previous approaches have addressed the disparate schema issue by learning candidate transformations of the meaning representation, in this paper, we instead model the reference resolution as a dialogue context-aware user query reformulation task {--} the dialog state is serialized to a sequence of natural language tokens representing the conversation. We develop our model for query reformulation using a pointer-generator network and a novel multi-task learning setup. In our experiments, we show a significant improvement in absolute F1 on an internal as well as a, soon to be released, public benchmark respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rastogi-etal-2019-scaling">
<titleInfo>
<title>Scaling Multi-Domain Dialogue State Tracking via Query Reformulation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pushpendre</namePart>
<namePart type="family">Rastogi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arpit</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tongfei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathias</namePart>
<namePart type="family">Lambert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastassia</namePart>
<namePart type="family">Loukina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michelle</namePart>
<namePart type="family">Morales</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohit</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the entities relevant to the conversation across turns. Tracking conversational state is particularly challenging in a multi-domain scenario when there exist multiple spoken language understanding (SLU) sub-systems, and each SLU sub-system operates on its domain-specific meaning representation. While previous approaches have addressed the disparate schema issue by learning candidate transformations of the meaning representation, in this paper, we instead model the reference resolution as a dialogue context-aware user query reformulation task – the dialog state is serialized to a sequence of natural language tokens representing the conversation. We develop our model for query reformulation using a pointer-generator network and a novel multi-task learning setup. In our experiments, we show a significant improvement in absolute F1 on an internal as well as a, soon to be released, public benchmark respectively.</abstract>
<identifier type="citekey">rastogi-etal-2019-scaling</identifier>
<identifier type="doi">10.18653/v1/N19-2013</identifier>
<location>
<url>https://aclanthology.org/N19-2013</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>97</start>
<end>105</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Scaling Multi-Domain Dialogue State Tracking via Query Reformulation
%A Rastogi, Pushpendre
%A Gupta, Arpit
%A Chen, Tongfei
%A Lambert, Mathias
%Y Loukina, Anastassia
%Y Morales, Michelle
%Y Kumar, Rohit
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F rastogi-etal-2019-scaling
%X We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the entities relevant to the conversation across turns. Tracking conversational state is particularly challenging in a multi-domain scenario when there exist multiple spoken language understanding (SLU) sub-systems, and each SLU sub-system operates on its domain-specific meaning representation. While previous approaches have addressed the disparate schema issue by learning candidate transformations of the meaning representation, in this paper, we instead model the reference resolution as a dialogue context-aware user query reformulation task – the dialog state is serialized to a sequence of natural language tokens representing the conversation. We develop our model for query reformulation using a pointer-generator network and a novel multi-task learning setup. In our experiments, we show a significant improvement in absolute F1 on an internal as well as a, soon to be released, public benchmark respectively.
%R 10.18653/v1/N19-2013
%U https://aclanthology.org/N19-2013
%U https://doi.org/10.18653/v1/N19-2013
%P 97-105
Markdown (Informal)
[Scaling Multi-Domain Dialogue State Tracking via Query Reformulation](https://aclanthology.org/N19-2013) (Rastogi et al., NAACL 2019)
ACL
- Pushpendre Rastogi, Arpit Gupta, Tongfei Chen, and Mathias Lambert. 2019. Scaling Multi-Domain Dialogue State Tracking via Query Reformulation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers), pages 97–105, Minneapolis, Minnesota. Association for Computational Linguistics.