@inproceedings{zhang-etal-2018-learning-control,
title = "Learning to Control the Specificity in Neural Response Generation",
author = "Zhang, Ruqing and
Guo, Jiafeng and
Fan, Yixing and
Lan, Yanyan and
Xu, Jun and
Cheng, Xueqi",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-1102/",
doi = "10.18653/v1/P18-1102",
pages = "1108--1117",
abstract = "In conversation, a general response (e.g., ``I don't know'') could correspond to a large variety of input utterances. Previous generative conversational models usually employ a single model to learn the relationship between different utterance-response pairs, thus tend to favor general and trivial responses which appear frequently. To address this problem, we propose a novel controlled response generation mechanism to handle different utterance-response relationships in terms of specificity. Specifically, we introduce an explicit specificity control variable into a sequence-to-sequence model, which interacts with the usage representation of words through a Gaussian Kernel layer, to guide the model to generate responses at different specificity levels. We describe two ways to acquire distant labels for the specificity control variable in learning. Empirical studies show that our model can significantly outperform the state-of-the-art response generation models under both automatic and human evaluations."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2018-learning-control">
<titleInfo>
<title>Learning to Control the Specificity in Neural Response Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruqing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiafeng</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixing</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanyan</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xueqi</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In conversation, a general response (e.g., “I don’t know”) could correspond to a large variety of input utterances. Previous generative conversational models usually employ a single model to learn the relationship between different utterance-response pairs, thus tend to favor general and trivial responses which appear frequently. To address this problem, we propose a novel controlled response generation mechanism to handle different utterance-response relationships in terms of specificity. Specifically, we introduce an explicit specificity control variable into a sequence-to-sequence model, which interacts with the usage representation of words through a Gaussian Kernel layer, to guide the model to generate responses at different specificity levels. We describe two ways to acquire distant labels for the specificity control variable in learning. Empirical studies show that our model can significantly outperform the state-of-the-art response generation models under both automatic and human evaluations.</abstract>
<identifier type="citekey">zhang-etal-2018-learning-control</identifier>
<identifier type="doi">10.18653/v1/P18-1102</identifier>
<location>
<url>https://aclanthology.org/P18-1102/</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>1108</start>
<end>1117</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Control the Specificity in Neural Response Generation
%A Zhang, Ruqing
%A Guo, Jiafeng
%A Fan, Yixing
%A Lan, Yanyan
%A Xu, Jun
%A Cheng, Xueqi
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F zhang-etal-2018-learning-control
%X In conversation, a general response (e.g., “I don’t know”) could correspond to a large variety of input utterances. Previous generative conversational models usually employ a single model to learn the relationship between different utterance-response pairs, thus tend to favor general and trivial responses which appear frequently. To address this problem, we propose a novel controlled response generation mechanism to handle different utterance-response relationships in terms of specificity. Specifically, we introduce an explicit specificity control variable into a sequence-to-sequence model, which interacts with the usage representation of words through a Gaussian Kernel layer, to guide the model to generate responses at different specificity levels. We describe two ways to acquire distant labels for the specificity control variable in learning. Empirical studies show that our model can significantly outperform the state-of-the-art response generation models under both automatic and human evaluations.
%R 10.18653/v1/P18-1102
%U https://aclanthology.org/P18-1102/
%U https://doi.org/10.18653/v1/P18-1102
%P 1108-1117
Markdown (Informal)
[Learning to Control the Specificity in Neural Response Generation](https://aclanthology.org/P18-1102/) (Zhang et al., ACL 2018)
ACL
- Ruqing Zhang, Jiafeng Guo, Yixing Fan, Yanyan Lan, Jun Xu, and Xueqi Cheng. 2018. Learning to Control the Specificity in Neural Response Generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1108–1117, Melbourne, Australia. Association for Computational Linguistics.