@inproceedings{zhang-etal-2019-recosa,
title = "{R}e{C}o{S}a: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation",
author = "Zhang, Hainan and
Lan, Yanyan and
Pang, Liang and
Guo, Jiafeng and
Cheng, Xueqi",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1362",
doi = "10.18653/v1/P19-1362",
pages = "3721--3730",
abstract = "In multi-turn dialogue generation, response is usually related with only a few contexts. Therefore, an ideal model should be able to detect these relevant contexts and produce a suitable response accordingly. However, the widely used hierarchical recurrent encoder-decoder models just treat all the contexts indiscriminately, which may hurt the following response generation process. Some researchers try to use the cosine similarity or the traditional attention mechanism to find the relevant contexts, but they suffer from either insufficient relevance assumption or position bias problem. In this paper, we propose a new model, named ReCoSa, to tackle this problem. Firstly, a word level LSTM encoder is conducted to obtain the initial representation of each context. Then, the self-attention mechanism is utilized to update both the context and masked response representation. Finally, the attention weights between each context and response representations are computed and used in the further decoding process. Experimental results on both Chinese customer services dataset and English Ubuntu dialogue dataset show that ReCoSa significantly outperforms baseline models, in terms of both metric-based and human evaluations. Further analysis on attention shows that the detected relevant contexts by ReCoSa are highly coherent with human{'}s understanding, validating the correctness and interpretability of ReCoSa.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2019-recosa">
<titleInfo>
<title>ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hainan</namePart>
<namePart type="family">Zhang</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">Liang</namePart>
<namePart type="family">Pang</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">Xueqi</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In multi-turn dialogue generation, response is usually related with only a few contexts. Therefore, an ideal model should be able to detect these relevant contexts and produce a suitable response accordingly. However, the widely used hierarchical recurrent encoder-decoder models just treat all the contexts indiscriminately, which may hurt the following response generation process. Some researchers try to use the cosine similarity or the traditional attention mechanism to find the relevant contexts, but they suffer from either insufficient relevance assumption or position bias problem. In this paper, we propose a new model, named ReCoSa, to tackle this problem. Firstly, a word level LSTM encoder is conducted to obtain the initial representation of each context. Then, the self-attention mechanism is utilized to update both the context and masked response representation. Finally, the attention weights between each context and response representations are computed and used in the further decoding process. Experimental results on both Chinese customer services dataset and English Ubuntu dialogue dataset show that ReCoSa significantly outperforms baseline models, in terms of both metric-based and human evaluations. Further analysis on attention shows that the detected relevant contexts by ReCoSa are highly coherent with human’s understanding, validating the correctness and interpretability of ReCoSa.</abstract>
<identifier type="citekey">zhang-etal-2019-recosa</identifier>
<identifier type="doi">10.18653/v1/P19-1362</identifier>
<location>
<url>https://aclanthology.org/P19-1362</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>3721</start>
<end>3730</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation
%A Zhang, Hainan
%A Lan, Yanyan
%A Pang, Liang
%A Guo, Jiafeng
%A Cheng, Xueqi
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F zhang-etal-2019-recosa
%X In multi-turn dialogue generation, response is usually related with only a few contexts. Therefore, an ideal model should be able to detect these relevant contexts and produce a suitable response accordingly. However, the widely used hierarchical recurrent encoder-decoder models just treat all the contexts indiscriminately, which may hurt the following response generation process. Some researchers try to use the cosine similarity or the traditional attention mechanism to find the relevant contexts, but they suffer from either insufficient relevance assumption or position bias problem. In this paper, we propose a new model, named ReCoSa, to tackle this problem. Firstly, a word level LSTM encoder is conducted to obtain the initial representation of each context. Then, the self-attention mechanism is utilized to update both the context and masked response representation. Finally, the attention weights between each context and response representations are computed and used in the further decoding process. Experimental results on both Chinese customer services dataset and English Ubuntu dialogue dataset show that ReCoSa significantly outperforms baseline models, in terms of both metric-based and human evaluations. Further analysis on attention shows that the detected relevant contexts by ReCoSa are highly coherent with human’s understanding, validating the correctness and interpretability of ReCoSa.
%R 10.18653/v1/P19-1362
%U https://aclanthology.org/P19-1362
%U https://doi.org/10.18653/v1/P19-1362
%P 3721-3730
Markdown (Informal)
[ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation](https://aclanthology.org/P19-1362) (Zhang et al., ACL 2019)
ACL