@inproceedings{yu-etal-2022-unsupervised,
title = "Unsupervised Slot Schema Induction for Task-oriented Dialog",
author = "Yu, Dian and
Wang, Mingqiu and
Cao, Yuan and
Shafran, Izhak and
Shafey, Laurent and
Soltau, Hagen",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.86",
doi = "10.18653/v1/2022.naacl-main.86",
pages = "1174--1193",
abstract = "Carefully-designed schemas describing how to collect and annotate dialog corpora are a prerequisite towards building task-oriented dialog systems. In practical applications, manually designing schemas can be error-prone, laborious, iterative, and slow, especially when the schema is complicated. To alleviate this expensive and time consuming process, we propose an unsupervised approach for slot schema induction from unlabeled dialog corpora. Leveraging in-domain language models and unsupervised parsing structures, our data-driven approach extracts candidate slots without constraints, followed by coarse-to-fine clustering to induce slot types. We compare our method against several strong supervised baselines, and show significant performance improvement in slot schema induction on MultiWoz and SGD datasets. We also demonstrate the effectiveness of induced schemas on downstream applications including dialog state tracking and response generation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2022-unsupervised">
<titleInfo>
<title>Unsupervised Slot Schema Induction for Task-oriented Dialog</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dian</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingqiu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Izhak</namePart>
<namePart type="family">Shafran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Shafey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hagen</namePart>
<namePart type="family">Soltau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Carefully-designed schemas describing how to collect and annotate dialog corpora are a prerequisite towards building task-oriented dialog systems. In practical applications, manually designing schemas can be error-prone, laborious, iterative, and slow, especially when the schema is complicated. To alleviate this expensive and time consuming process, we propose an unsupervised approach for slot schema induction from unlabeled dialog corpora. Leveraging in-domain language models and unsupervised parsing structures, our data-driven approach extracts candidate slots without constraints, followed by coarse-to-fine clustering to induce slot types. We compare our method against several strong supervised baselines, and show significant performance improvement in slot schema induction on MultiWoz and SGD datasets. We also demonstrate the effectiveness of induced schemas on downstream applications including dialog state tracking and response generation.</abstract>
<identifier type="citekey">yu-etal-2022-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.86</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.86</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1174</start>
<end>1193</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Slot Schema Induction for Task-oriented Dialog
%A Yu, Dian
%A Wang, Mingqiu
%A Cao, Yuan
%A Shafran, Izhak
%A Shafey, Laurent
%A Soltau, Hagen
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F yu-etal-2022-unsupervised
%X Carefully-designed schemas describing how to collect and annotate dialog corpora are a prerequisite towards building task-oriented dialog systems. In practical applications, manually designing schemas can be error-prone, laborious, iterative, and slow, especially when the schema is complicated. To alleviate this expensive and time consuming process, we propose an unsupervised approach for slot schema induction from unlabeled dialog corpora. Leveraging in-domain language models and unsupervised parsing structures, our data-driven approach extracts candidate slots without constraints, followed by coarse-to-fine clustering to induce slot types. We compare our method against several strong supervised baselines, and show significant performance improvement in slot schema induction on MultiWoz and SGD datasets. We also demonstrate the effectiveness of induced schemas on downstream applications including dialog state tracking and response generation.
%R 10.18653/v1/2022.naacl-main.86
%U https://aclanthology.org/2022.naacl-main.86
%U https://doi.org/10.18653/v1/2022.naacl-main.86
%P 1174-1193
Markdown (Informal)
[Unsupervised Slot Schema Induction for Task-oriented Dialog](https://aclanthology.org/2022.naacl-main.86) (Yu et al., NAACL 2022)
ACL
- Dian Yu, Mingqiu Wang, Yuan Cao, Izhak Shafran, Laurent Shafey, and Hagen Soltau. 2022. Unsupervised Slot Schema Induction for Task-oriented Dialog. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1174–1193, Seattle, United States. Association for Computational Linguistics.