Improved non-autoregressive dialog state tracking model

2021 ◽  
Author(s):  
Baizhen Li ◽  
Yibin Zhan ◽  
Zhihua Wei ◽  
Shi Huang ◽  
Lijun Sun
Author(s):  
Rudolf Kadlec ◽  
Miroslav Vodolan ◽  
Jindrich Libovicky ◽  
Jan Macek ◽  
Jan Kleindienst

Author(s):  
Seokhwan Kim ◽  
Luis Fernando D’Haro ◽  
Rafael E. Banchs ◽  
Jason D. Williams ◽  
Matthew Henderson

Author(s):  
Takaaki Hori ◽  
Hai Wang ◽  
Chiori Hori ◽  
Shinji Watanabe ◽  
Bret Harsham ◽  
...  

AI Magazine ◽  
2014 ◽  
Vol 35 (4) ◽  
pp. 121-124 ◽  
Author(s):  
Jason D. Williams ◽  
Matthew Henderson ◽  
Antoine Raux ◽  
Blaise Thomson ◽  
Alan Black ◽  
...  

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. The Dialog State Tracking Challenge is a research community challenge task that has run for three rounds. The challenge has given rise to a host of new methods for dialog state tracking, and also deeper understandings about the problem itself, including methods for evaluation.


2016 ◽  
Vol 7 (3) ◽  
pp. 34-46
Author(s):  
Julien Perez

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.


2014 ◽  
Author(s):  
Matthew Henderson ◽  
Blaise Thomson ◽  
Jason D Williams

2020 ◽  
Author(s):  
Adam Summerville ◽  
Jordan Hashemi ◽  
James Ryan ◽  
william ferguson

2020 ◽  
Vol 8 ◽  
pp. 556-571
Author(s):  
Jacob Andreas ◽  
John Bufe ◽  
David Burkett ◽  
Charles Chen ◽  
Josh Clausman ◽  
...  

We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends this graph. Programs include metacomputation operators for reference and revision that reuse dataflow fragments from previous turns. Our graph-based state enables the expression and manipulation of complex user intents, and explicit metacomputation makes these intents easier for learned models to predict. We introduce a new dataset, SMCalFlow, featuring complex dialogues about events, weather, places, and people. Experiments show that dataflow graphs and metacomputation substantially improve representability and predictability in these natural dialogues. Additional experiments on the MultiWOZ dataset show that our dataflow representation enables an otherwise off-the-shelf sequence-to-sequence model to match the best existing task-specific state tracking model. The SMCalFlow dataset, code for replicating experiments, and a public leaderboard are available at https://www.microsoft.com/en-us/research/project/dataflow-based-dialogue-semantic-machines .


Sign in / Sign up

Export Citation Format

Share Document