@inproceedings{santhanam-etal-2020-learning,
title = "Learning to Plan and Realize Separately for Open-Ended Dialogue Systems",
author = "Santhanam, Sashank and
Cheng, Zhuo and
Mather, Brodie and
Dorr, Bonnie and
Bhatia, Archna and
Hebenstreit, Bryanna and
Zemel, Alan and
Dalton, Adam and
Strzalkowski, Tomek and
Shaikh, Samira",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.247",
doi = "10.18653/v1/2020.findings-emnlp.247",
pages = "2736--2750",
abstract = "Achieving true human-like ability to conduct a conversation remains an elusive goal for open-ended dialogue systems. We posit this is because extant approaches towards natural language generation (NLG) are typically construed as end-to-end architectures that do not adequately model human generation processes. To investigate, we decouple generation into two separate phases: planning and realization. In the planning phase, we train two planners to generate plans for response utterances. The realization phase uses response plans to produce an appropriate response. Through rigorous evaluations, both automated and human, we demonstrate that decoupling the process into planning and realization performs better than an end-to-end approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="santhanam-etal-2020-learning">
<titleInfo>
<title>Learning to Plan and Realize Separately for Open-Ended Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sashank</namePart>
<namePart type="family">Santhanam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuo</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brodie</namePart>
<namePart type="family">Mather</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Dorr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Archna</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryanna</namePart>
<namePart type="family">Hebenstreit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Zemel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Dalton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomek</namePart>
<namePart type="family">Strzalkowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samira</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Achieving true human-like ability to conduct a conversation remains an elusive goal for open-ended dialogue systems. We posit this is because extant approaches towards natural language generation (NLG) are typically construed as end-to-end architectures that do not adequately model human generation processes. To investigate, we decouple generation into two separate phases: planning and realization. In the planning phase, we train two planners to generate plans for response utterances. The realization phase uses response plans to produce an appropriate response. Through rigorous evaluations, both automated and human, we demonstrate that decoupling the process into planning and realization performs better than an end-to-end approach.</abstract>
<identifier type="citekey">santhanam-etal-2020-learning</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.247</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.247</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2736</start>
<end>2750</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Plan and Realize Separately for Open-Ended Dialogue Systems
%A Santhanam, Sashank
%A Cheng, Zhuo
%A Mather, Brodie
%A Dorr, Bonnie
%A Bhatia, Archna
%A Hebenstreit, Bryanna
%A Zemel, Alan
%A Dalton, Adam
%A Strzalkowski, Tomek
%A Shaikh, Samira
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F santhanam-etal-2020-learning
%X Achieving true human-like ability to conduct a conversation remains an elusive goal for open-ended dialogue systems. We posit this is because extant approaches towards natural language generation (NLG) are typically construed as end-to-end architectures that do not adequately model human generation processes. To investigate, we decouple generation into two separate phases: planning and realization. In the planning phase, we train two planners to generate plans for response utterances. The realization phase uses response plans to produce an appropriate response. Through rigorous evaluations, both automated and human, we demonstrate that decoupling the process into planning and realization performs better than an end-to-end approach.
%R 10.18653/v1/2020.findings-emnlp.247
%U https://aclanthology.org/2020.findings-emnlp.247
%U https://doi.org/10.18653/v1/2020.findings-emnlp.247
%P 2736-2750
Markdown (Informal)
[Learning to Plan and Realize Separately for Open-Ended Dialogue Systems](https://aclanthology.org/2020.findings-emnlp.247) (Santhanam et al., Findings 2020)
ACL
- Sashank Santhanam, Zhuo Cheng, Brodie Mather, Bonnie Dorr, Archna Bhatia, Bryanna Hebenstreit, Alan Zemel, Adam Dalton, Tomek Strzalkowski, and Samira Shaikh. 2020. Learning to Plan and Realize Separately for Open-Ended Dialogue Systems. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2736–2750, Online. Association for Computational Linguistics.