@inproceedings{wang-etal-2018-teacher,
title = "A Teacher-Student Framework for Maintainable Dialog Manager",
author = "Wang, Weikang and
Zhang, Jiajun and
Zhang, Han and
Hwang, Mei-Yuh and
Zong, Chengqing and
Li, Zhifei",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1415",
doi = "10.18653/v1/D18-1415",
pages = "3803--3812",
abstract = "Reinforcement learning (RL) is an attractive solution for task-oriented dialog systems. However, extending RL-based systems to handle new intents and slots requires a system redesign. The high maintenance cost makes it difficult to apply RL methods to practical systems on a large scale. To address this issue, we propose a practical teacher-student framework to extend RL-based dialog systems without retraining from scratch. Specifically, the {``}student{''} is an extended dialog manager based on a new ontology, and the {``}teacher{''} is existing resources used for guiding the learning process of the {``}student{''}. By specifying constraints held in the new dialog manager, we transfer knowledge of the {``}teacher{''} to the {``}student{''} without additional resources. Experiments show that the performance of the extended system is comparable to the system trained from scratch. More importantly, the proposed framework makes no assumption about the unsupported intents and slots, which makes it possible to improve RL-based systems incrementally.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2018-teacher">
<titleInfo>
<title>A Teacher-Student Framework for Maintainable Dialog Manager</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weikang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei-Yuh</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhifei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Reinforcement learning (RL) is an attractive solution for task-oriented dialog systems. However, extending RL-based systems to handle new intents and slots requires a system redesign. The high maintenance cost makes it difficult to apply RL methods to practical systems on a large scale. To address this issue, we propose a practical teacher-student framework to extend RL-based dialog systems without retraining from scratch. Specifically, the “student” is an extended dialog manager based on a new ontology, and the “teacher” is existing resources used for guiding the learning process of the “student”. By specifying constraints held in the new dialog manager, we transfer knowledge of the “teacher” to the “student” without additional resources. Experiments show that the performance of the extended system is comparable to the system trained from scratch. More importantly, the proposed framework makes no assumption about the unsupported intents and slots, which makes it possible to improve RL-based systems incrementally.</abstract>
<identifier type="citekey">wang-etal-2018-teacher</identifier>
<identifier type="doi">10.18653/v1/D18-1415</identifier>
<location>
<url>https://aclanthology.org/D18-1415</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>3803</start>
<end>3812</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Teacher-Student Framework for Maintainable Dialog Manager
%A Wang, Weikang
%A Zhang, Jiajun
%A Zhang, Han
%A Hwang, Mei-Yuh
%A Zong, Chengqing
%A Li, Zhifei
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F wang-etal-2018-teacher
%X Reinforcement learning (RL) is an attractive solution for task-oriented dialog systems. However, extending RL-based systems to handle new intents and slots requires a system redesign. The high maintenance cost makes it difficult to apply RL methods to practical systems on a large scale. To address this issue, we propose a practical teacher-student framework to extend RL-based dialog systems without retraining from scratch. Specifically, the “student” is an extended dialog manager based on a new ontology, and the “teacher” is existing resources used for guiding the learning process of the “student”. By specifying constraints held in the new dialog manager, we transfer knowledge of the “teacher” to the “student” without additional resources. Experiments show that the performance of the extended system is comparable to the system trained from scratch. More importantly, the proposed framework makes no assumption about the unsupported intents and slots, which makes it possible to improve RL-based systems incrementally.
%R 10.18653/v1/D18-1415
%U https://aclanthology.org/D18-1415
%U https://doi.org/10.18653/v1/D18-1415
%P 3803-3812
Markdown (Informal)
[A Teacher-Student Framework for Maintainable Dialog Manager](https://aclanthology.org/D18-1415) (Wang et al., EMNLP 2018)
ACL
- Weikang Wang, Jiajun Zhang, Han Zhang, Mei-Yuh Hwang, Chengqing Zong, and Zhifei Li. 2018. A Teacher-Student Framework for Maintainable Dialog Manager. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3803–3812, Brussels, Belgium. Association for Computational Linguistics.