@inproceedings{xu-etal-2018-lsdscc,
title = "{LSDSCC}: a Large Scale Domain-Specific Conversational Corpus for Response Generation with Diversity Oriented Evaluation Metrics",
author = "Xu, Zhen and
Jiang, Nan and
Liu, Bingquan and
Rong, Wenge and
Wu, Bowen and
Wang, Baoxun and
Wang, Zhuoran and
Wang, Xiaolong",
editor = "Walker, Marilyn and
Ji, Heng and
Stent, Amanda",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-1188",
doi = "10.18653/v1/N18-1188",
pages = "2070--2080",
abstract = "It has been proven that automatic conversational agents can be built up using the Endto-End Neural Response Generation (NRG) framework, and such a data-driven methodology requires a large number of dialog pairs for model training and reasonable evaluation metrics for testing. This paper proposes a Large Scale Domain-Specific Conversational Corpus (LSDSCC) composed of high-quality queryresponse pairs extracted from the domainspecific online forum, with thorough preprocessing and cleansing procedures. Also, a testing set, including multiple diverse responses annotated for each query, is constructed, and on this basis, the metrics for measuring the diversity of generated results are further presented. We evaluate the performances of neural dialog models with the widely applied diversity boosting strategies on the proposed dataset. The experimental results have shown that our proposed corpus can be taken as a new benchmark dataset for the NRG task, and the presented metrics are promising to guide the optimization of NRG models by quantifying the diversity of the generated responses reasonably.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2018-lsdscc">
<titleInfo>
<title>LSDSCC: a Large Scale Domain-Specific Conversational Corpus for Response Generation with Diversity Oriented Evaluation Metrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bingquan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenge</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baoxun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuoran</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaolong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>It has been proven that automatic conversational agents can be built up using the Endto-End Neural Response Generation (NRG) framework, and such a data-driven methodology requires a large number of dialog pairs for model training and reasonable evaluation metrics for testing. This paper proposes a Large Scale Domain-Specific Conversational Corpus (LSDSCC) composed of high-quality queryresponse pairs extracted from the domainspecific online forum, with thorough preprocessing and cleansing procedures. Also, a testing set, including multiple diverse responses annotated for each query, is constructed, and on this basis, the metrics for measuring the diversity of generated results are further presented. We evaluate the performances of neural dialog models with the widely applied diversity boosting strategies on the proposed dataset. The experimental results have shown that our proposed corpus can be taken as a new benchmark dataset for the NRG task, and the presented metrics are promising to guide the optimization of NRG models by quantifying the diversity of the generated responses reasonably.</abstract>
<identifier type="citekey">xu-etal-2018-lsdscc</identifier>
<identifier type="doi">10.18653/v1/N18-1188</identifier>
<location>
<url>https://aclanthology.org/N18-1188</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>2070</start>
<end>2080</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LSDSCC: a Large Scale Domain-Specific Conversational Corpus for Response Generation with Diversity Oriented Evaluation Metrics
%A Xu, Zhen
%A Jiang, Nan
%A Liu, Bingquan
%A Rong, Wenge
%A Wu, Bowen
%A Wang, Baoxun
%A Wang, Zhuoran
%A Wang, Xiaolong
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F xu-etal-2018-lsdscc
%X It has been proven that automatic conversational agents can be built up using the Endto-End Neural Response Generation (NRG) framework, and such a data-driven methodology requires a large number of dialog pairs for model training and reasonable evaluation metrics for testing. This paper proposes a Large Scale Domain-Specific Conversational Corpus (LSDSCC) composed of high-quality queryresponse pairs extracted from the domainspecific online forum, with thorough preprocessing and cleansing procedures. Also, a testing set, including multiple diverse responses annotated for each query, is constructed, and on this basis, the metrics for measuring the diversity of generated results are further presented. We evaluate the performances of neural dialog models with the widely applied diversity boosting strategies on the proposed dataset. The experimental results have shown that our proposed corpus can be taken as a new benchmark dataset for the NRG task, and the presented metrics are promising to guide the optimization of NRG models by quantifying the diversity of the generated responses reasonably.
%R 10.18653/v1/N18-1188
%U https://aclanthology.org/N18-1188
%U https://doi.org/10.18653/v1/N18-1188
%P 2070-2080
Markdown (Informal)
[LSDSCC: a Large Scale Domain-Specific Conversational Corpus for Response Generation with Diversity Oriented Evaluation Metrics](https://aclanthology.org/N18-1188) (Xu et al., NAACL 2018)
ACL
- Zhen Xu, Nan Jiang, Bingquan Liu, Wenge Rong, Bowen Wu, Baoxun Wang, Zhuoran Wang, and Xiaolong Wang. 2018. LSDSCC: a Large Scale Domain-Specific Conversational Corpus for Response Generation with Diversity Oriented Evaluation Metrics. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2070–2080, New Orleans, Louisiana. Association for Computational Linguistics.