@inproceedings{he-etal-2020-amalgamating,
title = "Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training",
author = "He, Wanwei and
Yang, Min and
Yan, Rui and
Li, Chengming and
Shen, Ying and
Xu, Ruifeng",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.281",
doi = "10.18653/v1/2020.emnlp-main.281",
pages = "3498--3507",
abstract = "The challenge of both achieving task completion by querying the knowledge base and generating human-like responses for task-oriented dialogue systems is attracting increasing research attention. In this paper, we propose a {``}Two-Teacher One-Student{''} learning framework (TTOS) for task-oriented dialogue, with the goal of retrieving accurate KB entities and generating human-like responses simultaneously. TTOS amalgamates knowledge from two teacher networks that together provide comprehensive guidance to build a high-quality task-oriented dialogue system (student network). Each teacher network is trained via reinforcement learning with a goal-specific reward, which can be viewed as an expert towards the goal and transfers the professional characteristic to the student network. Instead of adopting the classic student-teacher learning of forcing the output of a student network to exactly mimic the soft targets produced by the teacher networks, we introduce two discriminators as in generative adversarial network (GAN) to transfer knowledge from two teachers to the student. The usage of discriminators relaxes the rigid coupling between the student and teachers. Extensive experiments on two benchmark datasets (i.e., CamRest and In-Car Assistant) demonstrate that TTOS significantly outperforms baseline methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2020-amalgamating">
<titleInfo>
<title>Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanwei</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengming</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</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>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>The challenge of both achieving task completion by querying the knowledge base and generating human-like responses for task-oriented dialogue systems is attracting increasing research attention. In this paper, we propose a “Two-Teacher One-Student” learning framework (TTOS) for task-oriented dialogue, with the goal of retrieving accurate KB entities and generating human-like responses simultaneously. TTOS amalgamates knowledge from two teacher networks that together provide comprehensive guidance to build a high-quality task-oriented dialogue system (student network). Each teacher network is trained via reinforcement learning with a goal-specific reward, which can be viewed as an expert towards the goal and transfers the professional characteristic to the student network. Instead of adopting the classic student-teacher learning of forcing the output of a student network to exactly mimic the soft targets produced by the teacher networks, we introduce two discriminators as in generative adversarial network (GAN) to transfer knowledge from two teachers to the student. The usage of discriminators relaxes the rigid coupling between the student and teachers. Extensive experiments on two benchmark datasets (i.e., CamRest and In-Car Assistant) demonstrate that TTOS significantly outperforms baseline methods.</abstract>
<identifier type="citekey">he-etal-2020-amalgamating</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.281</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.281</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3498</start>
<end>3507</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training
%A He, Wanwei
%A Yang, Min
%A Yan, Rui
%A Li, Chengming
%A Shen, Ying
%A Xu, Ruifeng
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F he-etal-2020-amalgamating
%X The challenge of both achieving task completion by querying the knowledge base and generating human-like responses for task-oriented dialogue systems is attracting increasing research attention. In this paper, we propose a “Two-Teacher One-Student” learning framework (TTOS) for task-oriented dialogue, with the goal of retrieving accurate KB entities and generating human-like responses simultaneously. TTOS amalgamates knowledge from two teacher networks that together provide comprehensive guidance to build a high-quality task-oriented dialogue system (student network). Each teacher network is trained via reinforcement learning with a goal-specific reward, which can be viewed as an expert towards the goal and transfers the professional characteristic to the student network. Instead of adopting the classic student-teacher learning of forcing the output of a student network to exactly mimic the soft targets produced by the teacher networks, we introduce two discriminators as in generative adversarial network (GAN) to transfer knowledge from two teachers to the student. The usage of discriminators relaxes the rigid coupling between the student and teachers. Extensive experiments on two benchmark datasets (i.e., CamRest and In-Car Assistant) demonstrate that TTOS significantly outperforms baseline methods.
%R 10.18653/v1/2020.emnlp-main.281
%U https://aclanthology.org/2020.emnlp-main.281
%U https://doi.org/10.18653/v1/2020.emnlp-main.281
%P 3498-3507
Markdown (Informal)
[Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training](https://aclanthology.org/2020.emnlp-main.281) (He et al., EMNLP 2020)
ACL