@inproceedings{liu-etal-2023-pvgru,
title = "{PVGRU}: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism",
author = {Liu, Yongkang and
Feng, Shi and
Wang, Daling and
Zhang, Yifei and
Sch{\"u}tze, Hinrich},
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.185",
doi = "10.18653/v1/2023.acl-long.185",
pages = "3295--3310",
abstract = "We investigate response generation for multi-turn dialogue in generative chatbots. Existing generative modelsbased on RNNs (Recurrent Neural Networks) usually employ the last hidden state to summarize the history, which makesmodels unable to capture the subtle variability observed in different dialogues and cannot distinguish the differencesbetween dialogues that are similar in composition. In this paper, we propose Pseudo-Variational Gated Recurrent Unit (PVGRU). The key novelty of PVGRU is a recurrent summarizing variable thataggregates the accumulated distribution variations of subsequences. We train PVGRU without relying on posterior knowledge, thus avoiding the training-inference inconsistency problem. PVGRU can perceive subtle semantic variability through summarizing variables that are optimized by two objectives we employ for training: distribution consistency and reconstruction. In addition, we build a Pseudo-Variational Hierarchical Dialogue(PVHD) model based on PVGRU. Experimental results demonstrate that PVGRU can broadly improve the diversity andrelevance of responses on two benchmark datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2023-pvgru">
<titleInfo>
<title>PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yongkang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shi</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daling</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schütze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We investigate response generation for multi-turn dialogue in generative chatbots. Existing generative modelsbased on RNNs (Recurrent Neural Networks) usually employ the last hidden state to summarize the history, which makesmodels unable to capture the subtle variability observed in different dialogues and cannot distinguish the differencesbetween dialogues that are similar in composition. In this paper, we propose Pseudo-Variational Gated Recurrent Unit (PVGRU). The key novelty of PVGRU is a recurrent summarizing variable thataggregates the accumulated distribution variations of subsequences. We train PVGRU without relying on posterior knowledge, thus avoiding the training-inference inconsistency problem. PVGRU can perceive subtle semantic variability through summarizing variables that are optimized by two objectives we employ for training: distribution consistency and reconstruction. In addition, we build a Pseudo-Variational Hierarchical Dialogue(PVHD) model based on PVGRU. Experimental results demonstrate that PVGRU can broadly improve the diversity andrelevance of responses on two benchmark datasets.</abstract>
<identifier type="citekey">liu-etal-2023-pvgru</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.185</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.185</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>3295</start>
<end>3310</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism
%A Liu, Yongkang
%A Feng, Shi
%A Wang, Daling
%A Zhang, Yifei
%A Schütze, Hinrich
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F liu-etal-2023-pvgru
%X We investigate response generation for multi-turn dialogue in generative chatbots. Existing generative modelsbased on RNNs (Recurrent Neural Networks) usually employ the last hidden state to summarize the history, which makesmodels unable to capture the subtle variability observed in different dialogues and cannot distinguish the differencesbetween dialogues that are similar in composition. In this paper, we propose Pseudo-Variational Gated Recurrent Unit (PVGRU). The key novelty of PVGRU is a recurrent summarizing variable thataggregates the accumulated distribution variations of subsequences. We train PVGRU without relying on posterior knowledge, thus avoiding the training-inference inconsistency problem. PVGRU can perceive subtle semantic variability through summarizing variables that are optimized by two objectives we employ for training: distribution consistency and reconstruction. In addition, we build a Pseudo-Variational Hierarchical Dialogue(PVHD) model based on PVGRU. Experimental results demonstrate that PVGRU can broadly improve the diversity andrelevance of responses on two benchmark datasets.
%R 10.18653/v1/2023.acl-long.185
%U https://aclanthology.org/2023.acl-long.185
%U https://doi.org/10.18653/v1/2023.acl-long.185
%P 3295-3310
Markdown (Informal)
[PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism](https://aclanthology.org/2023.acl-long.185) (Liu et al., ACL 2023)
ACL