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

页码：5725 / 5729

页数：5

共 50 条

[1] 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 - +
[2] 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 - +
[3] 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
[4] Spoken dialogue systems
Jokinen K.
McTear M.
Synthesis Lectures on Human Language Technologies, 2010, 2 (01): : 1 - 167
[5] Reinforcement learning for parameter estimation in statistical spoken dialogue systems
Jurcicek, Filip
Thomson, Blaise
Young, Steve
COMPUTER SPEECH AND LANGUAGE, 2012, 26 (03) : 168 - 192
[6] "HOW ROBUST R U?": EVALUATING TASK-ORIENTED DIALOGUE SYSTEMS ON SPOKEN CONVERSATIONS
Kim, Seokhwan
Liu, Yang
Fin, Di
Papangelis, Alexandros
Gopalakrishnan, Karthik
Hedayatnia, Behnam
Hakkani-Tur, Dilek
2021 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2021, : 1147 - 1154
[7] Online Learning of Attributed Bi-Automata for Dialogue Management in Spoken Dialogue Systems
Serras, Manex
Ines Torres, Maria
Del Pozo, Arantza
PATTERN RECOGNITION AND IMAGE ANALYSIS (IBPRIA 2017), 2017, 10255 : 22 - 31
[8] Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems
Su, Pei-Hao
Vandyke, David
Gasic, Milica
Kim, Dongho
Mrksic, Nikola
Wen, Tsung-Hsien
Young, Steve
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 2007 - 2011
[9] A Reinforcement Learning approach to evaluating state representations in spoken dialogue systems
Tetreault, Joel R.
Litman, Diane J.
SPEECH COMMUNICATION, 2008, 50 (8-9) : 683 - 696
[10] A model for incremental grounding in spoken dialogue systems
Thomas Visser
David Traum
David DeVault
Rieks op den Akker
Journal on Multimodal User Interfaces, 2014, 8 : 61 - 73

← 1 2 3 4 5 →