@inproceedings{quan-etal-2020-risawoz,
title = "{R}i{SAWOZ}: A Large-Scale Multi-Domain {W}izard-of-{O}z Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling",
author = "Quan, Jun and
Zhang, Shian and
Cao, Qian and
Li, Zizhong and
Xiong, Deyi",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.67/",
doi = "10.18653/v1/2020.emnlp-main.67",
pages = "930--940",
abstract = "In order to alleviate the shortage of multi-domain data and to capture discourse phenomena for task-oriented dialogue modeling, we propose RiSAWOZ, a large-scale multi-domain Chinese Wizard-of-Oz dataset with Rich Semantic Annotations. RiSAWOZ contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues, with more than 150K utterances spanning over 12 domains, which is larger than all previous annotated H2H conversational datasets. Both single- and multi-domain dialogues are constructed, accounting for 65{\%} and 35{\%}, respectively. Each dialogue is labeled with comprehensive dialogue annotations, including dialogue goal in the form of natural language description, domain, dialogue states and acts at both the user and system side. In addition to traditional dialogue annotations, we especially provide linguistic annotations on discourse phenomena, e.g., ellipsis and coreference, in dialogues, which are useful for dialogue coreference and ellipsis resolution tasks. Apart from the fully annotated dataset, we also present a detailed description of the data collection procedure, statistics and analysis of the dataset. A series of benchmark models and results are reported, including natural language understanding (intent detection {\&} slot filling), dialogue state tracking and dialogue context-to-text generation, as well as coreference and ellipsis resolution, which facilitate the baseline comparison for future research on this corpus."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="quan-etal-2020-risawoz">
<titleInfo>
<title>RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Quan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shian</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zizhong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In order to alleviate the shortage of multi-domain data and to capture discourse phenomena for task-oriented dialogue modeling, we propose RiSAWOZ, a large-scale multi-domain Chinese Wizard-of-Oz dataset with Rich Semantic Annotations. RiSAWOZ contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues, with more than 150K utterances spanning over 12 domains, which is larger than all previous annotated H2H conversational datasets. Both single- and multi-domain dialogues are constructed, accounting for 65% and 35%, respectively. Each dialogue is labeled with comprehensive dialogue annotations, including dialogue goal in the form of natural language description, domain, dialogue states and acts at both the user and system side. In addition to traditional dialogue annotations, we especially provide linguistic annotations on discourse phenomena, e.g., ellipsis and coreference, in dialogues, which are useful for dialogue coreference and ellipsis resolution tasks. Apart from the fully annotated dataset, we also present a detailed description of the data collection procedure, statistics and analysis of the dataset. A series of benchmark models and results are reported, including natural language understanding (intent detection & slot filling), dialogue state tracking and dialogue context-to-text generation, as well as coreference and ellipsis resolution, which facilitate the baseline comparison for future research on this corpus.</abstract>
<identifier type="citekey">quan-etal-2020-risawoz</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.67</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.67/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>930</start>
<end>940</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling
%A Quan, Jun
%A Zhang, Shian
%A Cao, Qian
%A Li, Zizhong
%A Xiong, Deyi
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F quan-etal-2020-risawoz
%X In order to alleviate the shortage of multi-domain data and to capture discourse phenomena for task-oriented dialogue modeling, we propose RiSAWOZ, a large-scale multi-domain Chinese Wizard-of-Oz dataset with Rich Semantic Annotations. RiSAWOZ contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues, with more than 150K utterances spanning over 12 domains, which is larger than all previous annotated H2H conversational datasets. Both single- and multi-domain dialogues are constructed, accounting for 65% and 35%, respectively. Each dialogue is labeled with comprehensive dialogue annotations, including dialogue goal in the form of natural language description, domain, dialogue states and acts at both the user and system side. In addition to traditional dialogue annotations, we especially provide linguistic annotations on discourse phenomena, e.g., ellipsis and coreference, in dialogues, which are useful for dialogue coreference and ellipsis resolution tasks. Apart from the fully annotated dataset, we also present a detailed description of the data collection procedure, statistics and analysis of the dataset. A series of benchmark models and results are reported, including natural language understanding (intent detection & slot filling), dialogue state tracking and dialogue context-to-text generation, as well as coreference and ellipsis resolution, which facilitate the baseline comparison for future research on this corpus.
%R 10.18653/v1/2020.emnlp-main.67
%U https://aclanthology.org/2020.emnlp-main.67/
%U https://doi.org/10.18653/v1/2020.emnlp-main.67
%P 930-940
Markdown (Informal)
[RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling](https://aclanthology.org/2020.emnlp-main.67/) (Quan et al., EMNLP 2020)
ACL