scholarly journals The Dialog State Tracking Challenge Series: A Review

2016 ◽  
Vol 7 (3) ◽  
pp. 4-33 ◽  
Author(s):  
Jason D. Williams ◽  
Antoine Raux ◽  
Matthew Henderson
Keyword(s):  
Speech Recognition ◽  
Research Area ◽  
The State ◽  
Evaluation Metrics ◽  
Common Resources ◽  
Discriminative Models ◽  
Dialog System ◽  
Spoken Dialog System ◽  
State Tracking ◽  
Dialog State Tracking

In a spoken dialog system, dialog state tracking refers to the task of correctly inferring the state of the conversation -- such as the user's goal -- given all of the dialog history up to that turn.  Dialog state tracking is crucial to the success of a dialog system, yet until recently there were no common resources, hampering progress.  The Dialog State Tracking Challenge series of 3 tasks introduced the first shared testbed and evaluation metrics for dialog state tracking, and has underpinned three key advances in dialog state tracking: the move from generative to discriminative models; the adoption of discriminative sequential techniques; and the incorporation of the speech recognition results directly into the dialog state tracker.  This paper reviews this research area, covering both the challenge tasks themselves and summarizing the work they have enabled.

scholarly journals Spectral decomposition method of dialog state tracking via collective matrix factorization

2016 ◽  
Vol 7 (3) ◽  
pp. 34-46
Author(s):  
Julien Perez
Keyword(s):  
Matrix Factorization ◽  
The State ◽  
Computationally Efficient ◽  
Reward Function ◽  
Dialog Management ◽  
Dialog System ◽  
Dependent Variables ◽  
Novel Method ◽  
State Tracking ◽  
Dialog State Tracking

The task of dialog management is commonly decomposed into two sequential subtasks: dialog state tracking and dialog policy learning. In an end-to-end dialog system, the aim of dialog state tracking is to accurately estimate the true dialog state from noisy observations produced by the speech recognition and the natural language understanding modules. The state tracking task is primarily meant to support a dialog policy. From a probabilistic perspective, this is achieved by maintaining a posterior distribution over hidden dialog states composed of a set of context dependent variables. Once a dialog policy is learned, it strives to select an optimal dialog act given the estimated dialog state and a defined reward function. This paper introduces a novel method of dialog state tracking based on a bilinear algebric decomposition model that provides an efficient inference schema through collective matrix factorization. We evaluate the proposed approach on the second Dialog State Tracking Challenge (DSTC-2) dataset and we show that the proposed tracker gives encouraging results compared to the state-of-the-art trackers that participated in this standard benchmark. Finally, we show that the prediction schema is computationally efficient in comparison to the previous approaches.

scholarly journals A Two-Step Neural Dialog State Tracker for Task-Oriented Dialog Processing

2018 ◽  
Vol 2018 ◽  
pp. 1-11
Author(s):  
A-Yeong Kim ◽  
Hyun-Je Song ◽  
Seong-Bae Park
Keyword(s):  
Attention Mechanism ◽  
Data Set ◽  
Dialog Systems ◽  
Dialog System ◽  
Fast Training ◽  
Proposed Model ◽  
Spoken Dialog System ◽  
State Tracking ◽  
Dialog State Tracking ◽  
Task Oriented

Dialog state tracking in a spoken dialog system is the task that tracks the flow of a dialog and identifies accurately what a user wants from the utterance. Since the success of a dialog is influenced by the ability of the system to catch the requirements of the user, accurate state tracking is important for spoken dialog systems. This paper proposes a two-step neural dialog state tracker which is composed of an informativeness classifier and a neural tracker. The informativeness classifier which is implemented by a CNN first filters out noninformative utterances in a dialog. Then, the neural tracker estimates dialog states from the remaining informative utterances. The tracker adopts the attention mechanism and the hierarchical softmax for its performance and fast training. To prove the effectiveness of the proposed model, we do experiments on dialog state tracking in the human-human task-oriented dialogs with the standard DSTC4 data set. Our experimental results prove the effectiveness of the proposed model by showing that the proposed model outperforms the neural trackers without the informativeness classifier, the attention mechanism, or the hierarchical softmax.

scholarly journals Recurrent Polynomial Network for Dialogue State Tracking

2016 ◽  
Vol 7 (3) ◽  
pp. 65-88
Author(s):  
Kai Sun ◽  
Qizhe Xie ◽  
Kai Yu
Keyword(s):  
State Of The Art ◽  
The State ◽  
Rule Based ◽  
The Third ◽  
Unique Structure ◽  
State Tracking ◽  
Dialog State Tracking ◽  
Statistical Approaches

  Dialogue state tracking (DST) is a process to estimate the distribution of the dialogue states as a dialogue progresses. Recent studies on constrained Markov Bayesian polynomial (CMBP) framework take the first step towards bridging the gap between rule-based and statistical approaches for DST. In this paper, the gap is further bridged by a novel framework -- recurrent polynomial network (RPN). RPN's unique structure enables the framework to have all the advantages of CMBP including efficiency, portability and interpretability. Additionally, RPN achieves more properties of statistical approaches than CMBP. RPN was evaluated on the data corpora of the second and the third Dialog State Tracking Challenge (DSTC-2/3). Experiments showed that RPN can significantly outperform both traditional rule-based approaches and statistical approaches with similar feature set. Compared with the state-of-the-art statistical DST approaches with a lot richer features, RPN is also competitive.

scholarly journals Concept Type Prediction and Responsive Adaptation in a Dialogue System

2012 ◽  
Vol 3 (1) ◽  
pp. 1-31 ◽  
Author(s):  
Svetlana Stoyanchev ◽  
Amanda J. Stent
Keyword(s):  
Speech Recognition ◽  
Recognition Performance ◽  
Language Model ◽  
Dialogue System ◽  
Dialog Systems ◽  
Language Model Adaptation ◽  
Dialog System ◽  
Spoken Dialog System ◽  
Type Classification ◽  
Concept Type

Responsive adaptation in spoken dialog systems involves a change in dialog system behavior in response to a user or a dialog situation. In this paper we address responsive adaptation in the automatic speech recognition (ASR) module of a spoken dialog system. We hypothesize that information about the content of a user utterance may help improve speech recognition for the utterance. We use a two-step process to test this hypothesis: first, we automatically predict the task-relevant concept types likely to be present in a user utterance using features from the dialog context and from the output of first-pass ASR of the utterance; and then, we adapt the ASR's language model to the predicted content of the user's utterance and run a second pass of ASR. We show that: (1) it is possible to achieve high accuracy in determining presence or absence of particular concept types in a post-confirmation utterance; and (2) 2-pass speech recognition with concept type classification and language model adaptation can lead to improved speech recognition performance for post-confirmation utterances.

scholarly journals Dialog History Construction with Long-Short Term Memory for Robust Generative Dialog State Tracking

2016 ◽  
Vol 7 (3) ◽  
pp. 47-64 ◽  
Author(s):  
Byung-Jun Lee ◽  
Kee-Eung Kim
Keyword(s):  
Speech Processing ◽  
Short Term Memory ◽  
Dialog Systems ◽  
Dialog System ◽  
Gradient Descent Algorithm ◽  
Core Areas ◽  
Overall Performance ◽  
Long Short Term Memory ◽  
State Tracking ◽  
Dialog State Tracking

One of the crucial components of dialog system is the dialog state tracker, which infers user’s intention from preliminary speech processing. Since the overall performance of the dialog system is heavily affected by that of the dialog tracker, it has been one of the core areas of research on dialog systems. In this paper, we present a dialog state tracker that combines a generative probabilistic model of dialog state tracking with the recurrent neural network for encoding important aspects of the dialog history. We describe a two-step gradient descent algorithm that optimizes the tracker with a complex loss function. We demonstrate that this approach yields a dialog state tracker that performs competitively with top-performing trackers participated in the first and second Dialog State Tracking Challenges.

Knowledge-based Dialog State Tracking

2014 ◽  
Author(s):  
Rudolf Kadlec ◽  
Miroslav Vodolan ◽  
Jindrich Libovicky ◽  
Jan Macek ◽  
Jan Kleindienst
Keyword(s):  
Knowledge Based ◽  
State Tracking ◽  
Dialog State Tracking

Probabilistic answer selection based on conditional random fields for spoken dialog system

2008 ◽  
Author(s):  
Yoshitaka Yoshimi ◽  
Ryota Kakitsuba ◽  
Yoshihiko Nankaku ◽  
Akinobu Lee ◽  
Keiichi Tokuda
Keyword(s):  
Random Fields ◽  
Conditional Random Fields ◽  
Dialog System ◽  
Spoken Dialog System

Spoken dialog system and its evaluation of geographic information system for elderly persons' mobility support

2005 ◽  
Author(s):  
Takatoshi Jitsuhiro ◽  
Shigeki Matsuda ◽  
Yutaka Ashikari ◽  
Satoshi Nakamura ◽  
Ikuko Eguchi Yairi ◽  
...  
Keyword(s):  
Information System ◽  
Geographic Information System ◽  
Geographic Information ◽  
Elderly Persons ◽  
Mobility Support ◽  
Dialog System ◽  
Spoken Dialog System

ANALYTICAL SUPPORT OF THE PROJECT COMPONENT CONTEXT IN THE CONTEXT OF THE INTEGRATED ASSESSMENT OF HUMAN RESOURCES BY TYPES OF ECONOMIC ACTIVITY

2017 ◽  
Author(s):  
Valeriya Yesina ◽  
◽  
Natalya Matvieieva ◽  
Dmitriy Novikov ◽  
◽  
...  
Keyword(s):  
Human Resources ◽  
Human Development ◽  
Economic Activity ◽  
Integrated Assessment ◽  
Professional Training ◽  
System Development ◽  
Research Area ◽  
The State ◽  
Industrial Complex ◽  
Personnel Costs

The article focuses on such a research area as human resources of the state. And their integrated assessment. The results obtained by type of economic activity are quite high, which is fully consistent with the dynamics of actual and future indicators. According to the Strategy of the state personnel policy, their content consists in: defining the tasks of the national personnel management system; development and implementation of a human development monitoring system; increasing labor productivity; calculation of efficiency and return on investment in human development; improving the national system of professional training taking into account the real needs of staff in the field of public administration, social and humanitarian sphere, key sectors of the economy, industry and agro-industrial complex. The procedure for analyzing human resources should begin with the choice of indicators. The final stage of the integrated long-term assessment of human resources is to determine the appropriate integrated indicator as a project component. The trends of each of the selected indicators for the calculation of the integrated indicator of human resources are constructed in the researched. Below are the equations of trends for the indicator "personnel costs of economic entities by type of economic activity", characterize, respectively, industry and construction and are presented in the form of exponential and linear relationships. This choice of trend equations is due to the dynamics of actual indicators.

Sign in / Sign up

Export Citation Format

Share Document