@inproceedings{wu-etal-2018-dialog,
title = "Dialog Generation Using Multi-Turn Reasoning Neural Networks",
author = "Wu, Xianchao and
Mart{\'\i}nez, Ander and
Klyen, Momo",
editor = "Walker, Marilyn and
Ji, Heng and
Stent, Amanda",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-1186",
doi = "10.18653/v1/N18-1186",
pages = "2049--2059",
abstract = "In this paper, we propose a generalizable dialog generation approach that adapts multi-turn reasoning, one recent advancement in the field of document comprehension, to generate responses ({``}answers{''}) by taking current conversation session context as a {``}document{''} and current query as a {``}question{''}. The major idea is to represent a conversation session into memories upon which attention-based memory reading mechanism can be performed multiple times, so that (1) user{'}s query is properly extended by contextual clues and (2) optimal responses are step-by-step generated. Considering that the speakers of one conversation are not limited to be one, we separate the single memory used for document comprehension into different groups for speaker-specific topic and opinion embedding. Namely, we utilize the queries{'} memory, the responses{'} memory, and their unified memory, following the time sequence of the conversation session. Experiments on Japanese 10-sentence (5-round) conversation modeling show impressive results on how multi-turn reasoning can produce more diverse and acceptable responses than state-of-the-art single-turn and non-reasoning baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2018-dialog">
<titleInfo>
<title>Dialog Generation Using Multi-Turn Reasoning Neural Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xianchao</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ander</namePart>
<namePart type="family">Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Momo</namePart>
<namePart type="family">Klyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose a generalizable dialog generation approach that adapts multi-turn reasoning, one recent advancement in the field of document comprehension, to generate responses (“answers”) by taking current conversation session context as a “document” and current query as a “question”. The major idea is to represent a conversation session into memories upon which attention-based memory reading mechanism can be performed multiple times, so that (1) user’s query is properly extended by contextual clues and (2) optimal responses are step-by-step generated. Considering that the speakers of one conversation are not limited to be one, we separate the single memory used for document comprehension into different groups for speaker-specific topic and opinion embedding. Namely, we utilize the queries’ memory, the responses’ memory, and their unified memory, following the time sequence of the conversation session. Experiments on Japanese 10-sentence (5-round) conversation modeling show impressive results on how multi-turn reasoning can produce more diverse and acceptable responses than state-of-the-art single-turn and non-reasoning baselines.</abstract>
<identifier type="citekey">wu-etal-2018-dialog</identifier>
<identifier type="doi">10.18653/v1/N18-1186</identifier>
<location>
<url>https://aclanthology.org/N18-1186</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>2049</start>
<end>2059</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dialog Generation Using Multi-Turn Reasoning Neural Networks
%A Wu, Xianchao
%A Martínez, Ander
%A Klyen, Momo
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F wu-etal-2018-dialog
%X In this paper, we propose a generalizable dialog generation approach that adapts multi-turn reasoning, one recent advancement in the field of document comprehension, to generate responses (“answers”) by taking current conversation session context as a “document” and current query as a “question”. The major idea is to represent a conversation session into memories upon which attention-based memory reading mechanism can be performed multiple times, so that (1) user’s query is properly extended by contextual clues and (2) optimal responses are step-by-step generated. Considering that the speakers of one conversation are not limited to be one, we separate the single memory used for document comprehension into different groups for speaker-specific topic and opinion embedding. Namely, we utilize the queries’ memory, the responses’ memory, and their unified memory, following the time sequence of the conversation session. Experiments on Japanese 10-sentence (5-round) conversation modeling show impressive results on how multi-turn reasoning can produce more diverse and acceptable responses than state-of-the-art single-turn and non-reasoning baselines.
%R 10.18653/v1/N18-1186
%U https://aclanthology.org/N18-1186
%U https://doi.org/10.18653/v1/N18-1186
%P 2049-2059
Markdown (Informal)
[Dialog Generation Using Multi-Turn Reasoning Neural Networks](https://aclanthology.org/N18-1186) (Wu et al., NAACL 2018)
ACL
- Xianchao Wu, Ander Martínez, and Momo Klyen. 2018. Dialog Generation Using Multi-Turn Reasoning Neural Networks. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2049–2059, New Orleans, Louisiana. Association for Computational Linguistics.