36484 shopping for clothes dialogue

Ngày tải lên: 27/08/2016, 21:35

Ngày tải lên: 27/08/2016, 19:33

... approach to exploit relational models of dialogue structure for controlling the action space in POMDPs This approach is part of an ongoing work to develop a unified framework for adaptive dialogue management ... foundations of relational POMDPs for dialogue (including how to specify the transition, observation and reward functions in such a relational framework), as wel...

Ngày tải lên: 20/02/2014, 04:20

... historical information, and Ω = {A1 , , Aq } is the set of DAs Using the maximum approximation for summation, (1) can be written as A = arg max t A Ω h (A, Ht ) = P r(At = A | At−1 ) W W = arg max ... Figure 2: An example of a dialogue management module using n-gram model for dialogue act sequence in the domain of historic spot Models for Dialogue Act Detection Re...

Ngày tải lên: 20/02/2014, 05:20

... integrate these with the topic knowledge We will also investigate further the relation between topics and speech acts, and specify their respective roles in context management for spoken dialogue systems ... entities in the dialogue and providing heuristics for different shifts of attention, we seek a formalisation of the information structure of utterances in terms of the new...

Ngày tải lên: 20/02/2014, 18:20

... multiple dialogue acts, according to manual dialogue act annotation Within the set of utterances that contain multiple dialogue acts, the average number of dialogue acts per utterance is 2.3 The dialogue ... number of words in utterances with only a single dialogue act is 7.5 (with a maximum of 34, and minimum of 1), and the average length of utterances with mu...

Ngày tải lên: 07/03/2014, 22:20

... developed for building dialogue systems using generic components We'll then describe two systems implemented using the TRIPS architecture that we will demonstrate at the interactive poster session Generic ... challenges For example: Information must flow asynchronously between dialogue components, so that actions can be triggered based on partial utterances even while...

Ngày tải lên: 08/03/2014, 04:22

... Johnston and S Bangalore 2000 Finite-state multimodal parsing and understanding In Proceedings of COLING 2000, Saarbr¨ cken, Germany u M Johnston and S Bangalore 2001 Finite-state methods for multimodal ... Boston S L Oviatt and J Clow 1998 An automated tool for analysis of multimodal system performance In Proceedings of ICSLP C Rich and C Sidner 1998 COLLAGEN: A collaboration man...

Ngày tải lên: 08/03/2014, 07:20

... as a good testbed for Targeted Help 2.2 The Targeted Help Module System Description 2.1 The WITAS Dialogue System Targeted Help was deployed and tested as part of the WITAS dialogue system l ... important focus for future dialogue system research Figure shows the structure of the Targeted Help component and its relationship to the rest of the dialogue system The goal of th...

Ngày tải lên: 08/03/2014, 21:20

... the general framework of NLG as planning under uncertainty (see (Lemon, 2008) for the initial version of this approach) Some aspects of NLG have been treated as planning, e.g (Koller and Stone, ... evaluated a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning After motivating and presenting the model, we studied...

Ngày tải lên: 08/03/2014, 21:20

... representation in other agents This is the case between the dialogue module and the problem solver for the problem formulation phase: a model of the expected problem is represented in the World For our ... for interpreting the literal meaning of the user's response returned by the INTERPRETER into its intended meaning within the particular game considered A simple example cons...

Ngày tải lên: 09/03/2014, 01:20

... modules, and thereby of Spoken Dialogue Systems in general Conclusion Acknowledgments We have presented a new data-driven method for Information Presentation (IP) in Spoken Dialogue Systems using ... Trainable sentence planning for complex information presentation in spoken dialog systems In Association for Computational Linguistics R Sutton and A Barto 1998 Reinforcem...

Ngày tải lên: 17/03/2014, 00:20

... State Update and Reinforcement Learning We build our dialogue system using the Information State Update approach (Larsson and Traum, 2000) and use Reinforcement Learning for action selection ... selected for each dialogue We train ten policies for each condition and turn-taking approach Policies are trained using Qlearning, and −greedy search for 10000 epochs (1 epoch = 100 dialog...

Ngày tải lên: 23/03/2014, 16:20