LEARNING CONCEPTS THROUGH CONVERSATIONS IN SPOKEN DIALOGUE SYSTEMS

被引：0

作者：

Jia, Robin ^{[1
]}

Heck, Larry ^{[2
]}

Hakkani-Tur, Dilek ^{[2
]}

Nikolov, Georgi ^{[2
]}

机构：

[1] Stanford Univ, Stanford, CA 94305 USA

[2] Google Res, Mountain View, CA USA

来源：

2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2017年

关键词：

Spoken dialogue systems; interactive learning;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Spoken dialogue systems must be able to recover gracefully from unexpected user inputs. In many cases, these unexpected utterances may be within the scope of the system, but include previously unseen phrases that the system cannot interpret. In this work, we augment a spoken dialogue system with the ability to learn about new concepts by conversing with the user in natural language. We present a novel model that detects phrases corresponding to such concepts, using information from a neural slotfiller as well as syntactic cues. The system then prompts the user for a definition of the detected phrases, and uses these definitions to re-parse the original utterance. We demonstrate significant gains by learning from the user, compared to a baseline system.

引用

下载

页码：5725 / 5729

页数：5

共 50 条

[1] Reinforcement learning for spoken dialogue systems
Singh, S
Kearns, M
Litman, D
Walker, M
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 12, 2000, 12 : 956 - 962
[2] Learning to ground in spoken dialogue systems
Pietquin, Olivier
2007 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol IV, Pts 1-3, 2007, : 165 - 168
[3] Machine Learning for Spoken Dialogue Systems
Lemon, Oliver
Pietquin, Olivier
INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 1761 - +
[4] LEARNING USER INTENTIONS IN SPOKEN DIALOGUE SYSTEMS
Chinaei, Hamid R.
Chaib-draa, Brahim
Lamontagne, Luc
ICAART 2009: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, 2009, : 107 - +
[5] Automatic learning of interpretation strategies for spoken dialogue systems
Raymond, C
Béchet, F
De Mori, R
Damnati, G
Estève, Y
2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING, 2004, : 425 - 428
[6] Statistical Spoken Dialogue Systems and the Challenges for Machine Learning
Young, Steve
WSDM'17: PROCEEDINGS OF THE TENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2017, : 577 - 577
[7] Transfer Learning for User Adaptation in Spoken Dialogue Systems
Genevay, Aude
Laroche, Romain
AAMAS'16: PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS & MULTIAGENT SYSTEMS, 2016, : 975 - 983
[8] User Simulation for Spoken Dialogue Systems: Learning and Evaluation
Georgila, Kallirroi
Henderson, James
Lenzon, Oliver
INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 1065 - 1068
[9] Spoken Dialogue Systems
Foster, Mary Ellen
COMPUTATIONAL LINGUISTICS, 2010, 36 (04) : 781 - 783
[10] Spoken dialogue systems
Jokinen K.
McTear M.
Synthesis Lectures on Human Language Technologies, 2010, 2 (01): : 1 - 167

← 1 2 3 4 5 →