@inproceedings{yavuz-etal-2019-deepcopy,
title = "{D}eep{C}opy: Grounded Response Generation with Hierarchical Pointer Networks",
author = "Yavuz, Semih and
Rastogi, Abhinav and
Chao, Guan-Lin and
Hakkani-Tur, Dilek",
editor = "Nakamura, Satoshi and
Gasic, Milica and
Zukerman, Ingrid and
Skantze, Gabriel and
Nakano, Mikio and
Papangelis, Alexandros and
Ultes, Stefan and
Yoshino, Koichiro",
booktitle = "Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue",
month = sep,
year = "2019",
address = "Stockholm, Sweden",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5917/",
doi = "10.18653/v1/W19-5917",
pages = "122--132",
abstract = "Recent advances in neural sequence-to-sequence models have led to promising results for several language generation-based tasks, including dialogue response generation, summarization, and machine translation. However, these models are known to have several problems, especially in the context of chit-chat based dialogue systems: they tend to generate short and dull responses that are often too generic. Furthermore, these models do not ground conversational responses on knowledge and facts, resulting in turns that are not accurate, informative and engaging for the users. In this paper, we propose and experiment with a series of response generation models that aim to serve in the general scenario where in addition to the dialogue context, relevant unstructured external knowledge in the form of text is also assumed to be available for models to harness. Our proposed approach extends pointer-generator networks (See et al., 2017) by allowing the decoder to hierarchically attend and copy from external knowledge in addition to the dialogue context. We empirically show the effectiveness of the proposed model compared to several baselines including (Ghazvininejadet al., 2018; Zhang et al., 2018) through both automatic evaluation metrics and human evaluation on ConvAI2 dataset."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yavuz-etal-2019-deepcopy">
<titleInfo>
<title>DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Semih</namePart>
<namePart type="family">Yavuz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Rastogi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guan-Lin</namePart>
<namePart type="family">Chao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milica</namePart>
<namePart type="family">Gasic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ingrid</namePart>
<namePart type="family">Zukerman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Skantze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikio</namePart>
<namePart type="family">Nakano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koichiro</namePart>
<namePart type="family">Yoshino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Stockholm, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in neural sequence-to-sequence models have led to promising results for several language generation-based tasks, including dialogue response generation, summarization, and machine translation. However, these models are known to have several problems, especially in the context of chit-chat based dialogue systems: they tend to generate short and dull responses that are often too generic. Furthermore, these models do not ground conversational responses on knowledge and facts, resulting in turns that are not accurate, informative and engaging for the users. In this paper, we propose and experiment with a series of response generation models that aim to serve in the general scenario where in addition to the dialogue context, relevant unstructured external knowledge in the form of text is also assumed to be available for models to harness. Our proposed approach extends pointer-generator networks (See et al., 2017) by allowing the decoder to hierarchically attend and copy from external knowledge in addition to the dialogue context. We empirically show the effectiveness of the proposed model compared to several baselines including (Ghazvininejadet al., 2018; Zhang et al., 2018) through both automatic evaluation metrics and human evaluation on ConvAI2 dataset.</abstract>
<identifier type="citekey">yavuz-etal-2019-deepcopy</identifier>
<identifier type="doi">10.18653/v1/W19-5917</identifier>
<location>
<url>https://aclanthology.org/W19-5917/</url>
</location>
<part>
<date>2019-09</date>
<extent unit="page">
<start>122</start>
<end>132</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks
%A Yavuz, Semih
%A Rastogi, Abhinav
%A Chao, Guan-Lin
%A Hakkani-Tur, Dilek
%Y Nakamura, Satoshi
%Y Gasic, Milica
%Y Zukerman, Ingrid
%Y Skantze, Gabriel
%Y Nakano, Mikio
%Y Papangelis, Alexandros
%Y Ultes, Stefan
%Y Yoshino, Koichiro
%S Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
%D 2019
%8 September
%I Association for Computational Linguistics
%C Stockholm, Sweden
%F yavuz-etal-2019-deepcopy
%X Recent advances in neural sequence-to-sequence models have led to promising results for several language generation-based tasks, including dialogue response generation, summarization, and machine translation. However, these models are known to have several problems, especially in the context of chit-chat based dialogue systems: they tend to generate short and dull responses that are often too generic. Furthermore, these models do not ground conversational responses on knowledge and facts, resulting in turns that are not accurate, informative and engaging for the users. In this paper, we propose and experiment with a series of response generation models that aim to serve in the general scenario where in addition to the dialogue context, relevant unstructured external knowledge in the form of text is also assumed to be available for models to harness. Our proposed approach extends pointer-generator networks (See et al., 2017) by allowing the decoder to hierarchically attend and copy from external knowledge in addition to the dialogue context. We empirically show the effectiveness of the proposed model compared to several baselines including (Ghazvininejadet al., 2018; Zhang et al., 2018) through both automatic evaluation metrics and human evaluation on ConvAI2 dataset.
%R 10.18653/v1/W19-5917
%U https://aclanthology.org/W19-5917/
%U https://doi.org/10.18653/v1/W19-5917
%P 122-132
Markdown (Informal)
[DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks](https://aclanthology.org/W19-5917/) (Yavuz et al., SIGDIAL 2019)
ACL