@inproceedings{chen-etal-2019-semantically,
title = "Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention",
author = "Chen, Wenhu and
Chen, Jianshu and
Qin, Pengda and
Yan, Xifeng and
Wang, William Yang",
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/P19-1360",
doi = "10.18653/v1/P19-1360",
pages = "3696--3709",
abstract = "Semantically controlled neural response generation on limited-domain has achieved great performance. However, moving towards multi-domain large-scale scenarios are shown to be difficult because the possible combinations of semantic inputs grow exponentially with the number of domains. To alleviate such scalability issue, we exploit the structure of dialog acts to build a multi-layer hierarchical graph, where each act is represented as a root-to-leaf route on the graph. Then, we incorporate such graph structure prior as an inductive bias to build a hierarchical disentangled self-attention network, where we disentangle attention heads to model designated nodes on the dialog act graph. By activating different (disentangled) heads at each layer, combinatorially many dialog act semantics can be modeled to control the neural response generation. On the large-scale Multi-Domain-WOZ dataset, our model can yield a significant improvement over the baselines on various automatic and human evaluation metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2019-semantically">
<titleInfo>
<title>Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenhu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianshu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengda</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xifeng</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">Yang</namePart>
<namePart type="family">Wang</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>Semantically controlled neural response generation on limited-domain has achieved great performance. However, moving towards multi-domain large-scale scenarios are shown to be difficult because the possible combinations of semantic inputs grow exponentially with the number of domains. To alleviate such scalability issue, we exploit the structure of dialog acts to build a multi-layer hierarchical graph, where each act is represented as a root-to-leaf route on the graph. Then, we incorporate such graph structure prior as an inductive bias to build a hierarchical disentangled self-attention network, where we disentangle attention heads to model designated nodes on the dialog act graph. By activating different (disentangled) heads at each layer, combinatorially many dialog act semantics can be modeled to control the neural response generation. On the large-scale Multi-Domain-WOZ dataset, our model can yield a significant improvement over the baselines on various automatic and human evaluation metrics.</abstract>
<identifier type="citekey">chen-etal-2019-semantically</identifier>
<identifier type="doi">10.18653/v1/P19-1360</identifier>
<location>
<url>https://aclanthology.org/P19-1360</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>3696</start>
<end>3709</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
%A Chen, Wenhu
%A Chen, Jianshu
%A Qin, Pengda
%A Yan, Xifeng
%A Wang, William Yang
%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 chen-etal-2019-semantically
%X Semantically controlled neural response generation on limited-domain has achieved great performance. However, moving towards multi-domain large-scale scenarios are shown to be difficult because the possible combinations of semantic inputs grow exponentially with the number of domains. To alleviate such scalability issue, we exploit the structure of dialog acts to build a multi-layer hierarchical graph, where each act is represented as a root-to-leaf route on the graph. Then, we incorporate such graph structure prior as an inductive bias to build a hierarchical disentangled self-attention network, where we disentangle attention heads to model designated nodes on the dialog act graph. By activating different (disentangled) heads at each layer, combinatorially many dialog act semantics can be modeled to control the neural response generation. On the large-scale Multi-Domain-WOZ dataset, our model can yield a significant improvement over the baselines on various automatic and human evaluation metrics.
%R 10.18653/v1/P19-1360
%U https://aclanthology.org/P19-1360
%U https://doi.org/10.18653/v1/P19-1360
%P 3696-3709
Markdown (Informal)
[Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention](https://aclanthology.org/P19-1360) (Chen et al., ACL 2019)
ACL