@inproceedings{li-etal-2019-sampling,
title = "Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems",
author = "Li, Jia and
Tao, Chongyang and
Wu, Wei and
Feng, Yansong and
Zhao, Dongyan and
Yan, Rui",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1128",
doi = "10.18653/v1/D19-1128",
pages = "1291--1296",
abstract = "We study how to sample negative examples to automatically construct a training set for effective model learning in retrieval-based dialogue systems. Following an idea of dynamically adapting negative examples to matching models in learning, we consider four strategies including minimum sampling, maximum sampling, semi-hard sampling, and decay-hard sampling. Empirical studies on two benchmarks with three matching models indicate that compared with the widely used random sampling strategy, although the first two strategies lead to performance drop, the latter two ones can bring consistent improvement to the performance of all the models on both benchmarks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2019-sampling">
<titleInfo>
<title>Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jia</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chongyang</namePart>
<namePart type="family">Tao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yansong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongyan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study how to sample negative examples to automatically construct a training set for effective model learning in retrieval-based dialogue systems. Following an idea of dynamically adapting negative examples to matching models in learning, we consider four strategies including minimum sampling, maximum sampling, semi-hard sampling, and decay-hard sampling. Empirical studies on two benchmarks with three matching models indicate that compared with the widely used random sampling strategy, although the first two strategies lead to performance drop, the latter two ones can bring consistent improvement to the performance of all the models on both benchmarks.</abstract>
<identifier type="citekey">li-etal-2019-sampling</identifier>
<identifier type="doi">10.18653/v1/D19-1128</identifier>
<location>
<url>https://aclanthology.org/D19-1128</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1291</start>
<end>1296</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems
%A Li, Jia
%A Tao, Chongyang
%A Wu, Wei
%A Feng, Yansong
%A Zhao, Dongyan
%A Yan, Rui
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F li-etal-2019-sampling
%X We study how to sample negative examples to automatically construct a training set for effective model learning in retrieval-based dialogue systems. Following an idea of dynamically adapting negative examples to matching models in learning, we consider four strategies including minimum sampling, maximum sampling, semi-hard sampling, and decay-hard sampling. Empirical studies on two benchmarks with three matching models indicate that compared with the widely used random sampling strategy, although the first two strategies lead to performance drop, the latter two ones can bring consistent improvement to the performance of all the models on both benchmarks.
%R 10.18653/v1/D19-1128
%U https://aclanthology.org/D19-1128
%U https://doi.org/10.18653/v1/D19-1128
%P 1291-1296
Markdown (Informal)
[Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems](https://aclanthology.org/D19-1128) (Li et al., EMNLP-IJCNLP 2019)
ACL