Results 1 - 10 of 580

The Dialog State Tracking Challenge

by Jason Williams, Antoine Raux, Deepak Ramach, Alan Black
"... In a spoken dialog system, dialog state tracking deduces information about the user’s goal as the dialog progresses, synthesizing evidence such as dialog acts over multiple turns with external data sources. Recent approaches have been shown to overcome ASR and SLU errors in some applications. Howeve ..."
Abstract - Cited by 20 (6 self) - Add to MetaCart
In a spoken dialog system, dialog state tracking deduces information about the user’s goal as the dialog progresses, synthesizing evidence such as dialog acts over multiple turns with external data sources. Recent approaches have been shown to overcome ASR and SLU errors in some applications

THE FIFTH DIALOG STATE TRACKING CHALLENGE

by Seokhwan Kim , Luis Fernando D'haro , Rafael E Banchs , Jason D Williams , Matthew Henderson , Koichiro Yoshino
"... ABSTRACT Dialog state tracking -the process of updating the dialog state after each interaction with the user -is a key component of most dialog systems. Following a similar scheme to the fourth dialog state tracking challenge, this edition again focused on human-human dialogs, but introduced the t ..."
Abstract - Add to MetaCart
ABSTRACT Dialog state tracking -the process of updating the dialog state after each interaction with the user -is a key component of most dialog systems. Following a similar scheme to the fourth dialog state tracking challenge, this edition again focused on human-human dialogs, but introduced

The second dialog state tracking challenge

by Matthew Henderson, Blaise Thomson, Jason Williams - In Proceedings of the SIGdial 2014 Conference , 2014
"... A spoken dialog system, while commu-nicating with a user, must keep track of what the user wants from the system at each step. This process, termed dialog state tracking, is essential for a success-ful dialog system as it directly informs the system’s actions. The first Dialog State Tracking Challen ..."
Abstract - Cited by 15 (6 self) - Add to MetaCart
A spoken dialog system, while commu-nicating with a user, must keep track of what the user wants from the system at each step. This process, termed dialog state tracking, is essential for a success-ful dialog system as it directly informs the system’s actions. The first Dialog State Tracking

THE THIRD DIALOG STATE TRACKING CHALLENGE

by Matthew Henderson, Blaise Thomson, Jason D. Williams
"... In spoken dialog systems, dialog state tracking refers to the task of correctly inferring the user’s goal at a given turn, given all of the dialog history up to that turn. This task is chal-lenging because of speech recognition and language under-standing errors, yet good dialog state tracking is cr ..."
Abstract - Cited by 3 (2 self) - Add to MetaCart
In spoken dialog systems, dialog state tracking refers to the task of correctly inferring the user’s goal at a given turn, given all of the dialog history up to that turn. This task is chal-lenging because of speech recognition and language under-standing errors, yet good dialog state tracking

Comparative Error Analysis of Dialog State Tracking

by Ronnie W. Smith
"... A primary motivation of the Dialog State Tracking Challenge (DSTC) is to allow for direct comparisons between alterna-tive approaches to dialog state tracking. While results from DSTC 1 mention per-formance limitations, an examination of the errors made by dialog state trackers was not discussed in ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
A primary motivation of the Dialog State Tracking Challenge (DSTC) is to allow for direct comparisons between alterna-tive approaches to dialog state tracking. While results from DSTC 1 mention per-formance limitations, an examination of the errors made by dialog state trackers was not discussed

Dialog State Tracking using Conditional Random Fields

by Hang Ren, Weiqun Xu, Yan Zhang, Yonghong Yan
"... This paper presents our approach to dialog state tracking for the Dialog State Tracking Challenge task. In our approach we use discriminative general structured conditional random fields, instead of traditional generative directed graphic models, to incorporate arbitrary overlapping features. Our ap ..."
Abstract - Cited by 5 (0 self) - Add to MetaCart
This paper presents our approach to dialog state tracking for the Dialog State Tracking Challenge task. In our approach we use discriminative general structured conditional random fields, instead of traditional generative directed graphic models, to incorporate arbitrary overlapping features. Our

Annotations for dynamic diagnosis of the dialog state

by Laurence Devillers, Sophie Rosset, Hélène Bonneau-maynard, Lori Lamel - In: LREC. European Language Resources Association , 2002
"... This paper describes recent work aimed at relating multi-level dialog annotations with meta-data annotations for a corpus of real humanhuman dialogs. This work is carried out in the context of the AMITIES project in which spoken dialog systems for call center services are being developed. A corpus o ..."
Abstract - Cited by 6 (2 self) - Add to MetaCart
This paper describes recent work aimed at relating multi-level dialog annotations with meta-data annotations for a corpus of real humanhuman dialogs. This work is carried out in the context of the AMITIES project in which spoken dialog systems for call center services are being developed. A corpus

Sequential Labeling for Tracking Dynamic Dialog States

by Seokhwan Kim, Rafael E. Banchs
"... This paper presents a sequential labeling approach for tracking the dialog states for the cases of goal changes in a dialog ses-sion. The tracking models are trained us-ing linear-chain conditional random fields with the features obtained from the results of SLU. The experimental results show that o ..."
Abstract - Add to MetaCart
This paper presents a sequential labeling approach for tracking the dialog states for the cases of goal changes in a dialog ses-sion. The tracking models are trained us-ing linear-chain conditional random fields with the features obtained from the results of SLU. The experimental results show

Multi-domain learning and generalization in dialog state tracking

by Jason D Williams - In Proceedings of SIGDIAL , 2013
"... Abstract Statistical approaches to dialog state tracking synthesize information across multiple turns in the dialog, overcoming some speech recognition errors. When training a dialog state tracker, there is typically only a small corpus of well-matched dialog data available. However, often there is ..."
Abstract - Cited by 6 (1 self) - Add to MetaCart
Abstract Statistical approaches to dialog state tracking synthesize information across multiple turns in the dialog, overcoming some speech recognition errors. When training a dialog state tracker, there is typically only a small corpus of well-matched dialog data available. However, often

Recipe For Building Robust Spoken Dialog State Trackers: Dialog State Tracking Challenge System Description

by Sungjin Lee, Maxine Eskenazi , 2013
"... For robust spoken conversational interaction, many dialog state tracking algorithms have been developed. Few studies, however, have reported the strengths and weaknesses of each method. The Dialog State Tracking Challenge (DSTC) is designed to address this issue by comparing various methods on the s ..."
Abstract - Cited by 8 (2 self) - Add to MetaCart
For robust spoken conversational interaction, many dialog state tracking algorithms have been developed. Few studies, however, have reported the strengths and weaknesses of each method. The Dialog State Tracking Challenge (DSTC) is designed to address this issue by comparing various methods
Results 1 - 10 of 580