@inproceedings{huang-etal-2020-generalizable,
title = "Generalizable and Explainable Dialogue Generation via Explicit Action Learning",
author = "Huang, Xinting and
Qi, Jianzhong and
Sun, Yu and
Zhang, Rui",
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.355",
doi = "10.18653/v1/2020.findings-emnlp.355",
pages = "3981--3991",
abstract = "Response generation for task-oriented dialogues implicitly optimizes two objectives at the same time: task completion and language quality. Conditioned response generation serves as an effective approach to separately and better optimize these two objectives. Such an approach relies on system action annotations which are expensive to obtain. To alleviate the need of action annotations, latent action learning is introduced to map each utterance to a latent representation. However, this approach is prone to over-dependence on the training data, and the generalization capability is thus restricted. To address this issue, we propose to learn \textit{natural language actions} that represent utterances as a span of words. This explicit action representation promotes generalization via the compositional structure of language. It also enables an explainable generation process. Our proposed unsupervised approach learns a memory component to summarize system utterances into a short span of words. To further promote a compact action representation, we propose an auxiliary task that restores state annotations as the summarized dialogue context using the memory component. Our proposed approach outperforms latent action baselines on MultiWOZ, a benchmark multi-domain dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2020-generalizable">
<titleInfo>
<title>Generalizable and Explainable Dialogue Generation via Explicit Action Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinting</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianzhong</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhang</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>Response generation for task-oriented dialogues implicitly optimizes two objectives at the same time: task completion and language quality. Conditioned response generation serves as an effective approach to separately and better optimize these two objectives. Such an approach relies on system action annotations which are expensive to obtain. To alleviate the need of action annotations, latent action learning is introduced to map each utterance to a latent representation. However, this approach is prone to over-dependence on the training data, and the generalization capability is thus restricted. To address this issue, we propose to learn natural language actions that represent utterances as a span of words. This explicit action representation promotes generalization via the compositional structure of language. It also enables an explainable generation process. Our proposed unsupervised approach learns a memory component to summarize system utterances into a short span of words. To further promote a compact action representation, we propose an auxiliary task that restores state annotations as the summarized dialogue context using the memory component. Our proposed approach outperforms latent action baselines on MultiWOZ, a benchmark multi-domain dataset.</abstract>
<identifier type="citekey">huang-etal-2020-generalizable</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.355</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.355</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3981</start>
<end>3991</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generalizable and Explainable Dialogue Generation via Explicit Action Learning
%A Huang, Xinting
%A Qi, Jianzhong
%A Sun, Yu
%A Zhang, Rui
%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 huang-etal-2020-generalizable
%X Response generation for task-oriented dialogues implicitly optimizes two objectives at the same time: task completion and language quality. Conditioned response generation serves as an effective approach to separately and better optimize these two objectives. Such an approach relies on system action annotations which are expensive to obtain. To alleviate the need of action annotations, latent action learning is introduced to map each utterance to a latent representation. However, this approach is prone to over-dependence on the training data, and the generalization capability is thus restricted. To address this issue, we propose to learn natural language actions that represent utterances as a span of words. This explicit action representation promotes generalization via the compositional structure of language. It also enables an explainable generation process. Our proposed unsupervised approach learns a memory component to summarize system utterances into a short span of words. To further promote a compact action representation, we propose an auxiliary task that restores state annotations as the summarized dialogue context using the memory component. Our proposed approach outperforms latent action baselines on MultiWOZ, a benchmark multi-domain dataset.
%R 10.18653/v1/2020.findings-emnlp.355
%U https://aclanthology.org/2020.findings-emnlp.355
%U https://doi.org/10.18653/v1/2020.findings-emnlp.355
%P 3981-3991
Markdown (Informal)
[Generalizable and Explainable Dialogue Generation via Explicit Action Learning](https://aclanthology.org/2020.findings-emnlp.355) (Huang et al., Findings 2020)
ACL