Filters








5,986 Hits in 9.1 sec

A Corpus-Based Approach for Cooperative Response Generation in a Dialog System [chapter]

Zhiyong Wu, Helen Meng, Hui Ning, Sam C. Tse
2006 Lecture Notes in Computer Science  
This paper presents a corpus-based approach for cooperative response generation in a spoken dialog system for the Hong Kong tourism domain.  ...  and system response in the dialog.  ...  Conclusions and Future Work This paper presents a corpus-based approach for cooperative response generation in a spoken dialog system for the Hong Kong tourism domain.  ... 
doi:10.1007/11939993_63 fatcat:wmse6f5rezbvtdwa4wcipd334m

Response type selection for chat-like spoken dialog systems based on LSTM and multi-task learning

Kengo Ohta, Ryota Nishimura, Norihide Kitaoka
2021 Speech Communication  
Kitaoka, Response type selection for chat-like spoken dialog systems based on LSTM and multi-task learning. Speech Communication (2021), doi: https://doi.  ...  Abstract We propose a method of automatically selecting appropriate responses in conversational spoken dialog systems by explicitly determining the correct response type that is needed first, based on  ...  Acknowledgments This work was supported in part by the Strategic Information and Com-  ... 
doi:10.1016/j.specom.2021.07.003 fatcat:owbm3rkqqfbifcfhyclbq2azzi

Measuring the differences between human-human and human-machine dialogs

David GRIOL, José MOLINA
2015 Advances in Distributed Computing and Artificial Intelligence Journal  
Finally, a dialog simulation technique has been developed for the acquisition of the third corpus.  ...  This technique uses a random selection of the user and system turns, defining stop conditions for automatically deciding if the simulated dialog is successful or not.  ...  In our dialog generation technique, both agents use a random selection of one of the possible responses defined for the semantics of the task (expressed in terms of user and system dialog acts).  ... 
doi:10.14201/adcaij20154299112 fatcat:bhggmurbizdwdkrdt3kqv35eda

AN AUTOMATIC DIALOG SIMULATION TECHNIQUE TO DEVELOP AND EVALUATE INTERACTIVE CONVERSATIONAL AGENTS

David Griol, Javier Carbó, José M. Molina
2013 Applied Artificial Intelligence  
In this article, we present an agent based dialog simulation technique for learning new dialog strategies and evaluating con versational agents.  ...  The results of the comparison of these measures for an initial corpus and a corpus acquired using the dialog simulation technique show that the conversational agent reduces the time needed to complete  ...  In our dialog generation technique, both agents use a random selection of one of the possible responses defined for the semantics of the task (expressed in terms of user and system dialog acts).  ... 
doi:10.1080/08839514.2013.835230 fatcat:7eiybglcdzappeaqrhr4ypckoq

Simulating heterogeneous user behaviors to interact with conversational interfaces

David GRIOL, Jose Manuel MOLINA
2016 Advances in Distributed Computing and Artificial Intelligence Journal  
The selection of the user responses by the simulated user are based on a statistical model that considers the complete history of the interaction to carry out this selection.  ...  that are selected by the system.  ...  A summary of corpus-based user modeling techniques for reinforcement learning of the dialog strategy can be found in (Schatzmann et al., 2006) .  ... 
doi:10.14201/adcaij2016545969 fatcat:5jcodjrmuzculayf6gc37s2dyi

An Agent-Based Dialog Simulation Technique to Develop and Evaluate Conversational Agents [chapter]

David Griol, Nayat Sánchez-Pi, Javier Carbó, José M. Molina
2011 Advances in Intelligent and Soft Computing  
In this paper, we present an agent-based dialog simulation technique for learning new dialog strategies and evaluate conversational agents.  ...  We have applied this technique to explore the space of possible dialog strategies and evaluate the dialogs acquired for a conversational agent that collects monitored data from patients suffering from  ...  In our dialog generation technique, both agents use a random selection of one of the possible responses defined for the semantics of the task (expressed in terms of user and system dialog acts).  ... 
doi:10.1007/978-3-642-19875-5_33 dblp:conf/paams/GriolPCM11 fatcat:h5kgylx2uzdrfgmqsjdtqfiejm

Predicting User Satisfaction in Spoken Dialog System Evaluation With Collaborative Filtering

Zhaojun Yang, Gina-Anne Levow, Helen Meng
2012 IEEE Journal on Selected Topics in Signal Processing  
We also demonstrate the generalizability of the CF model to a new dialog corpus from the systems in the Spoken Dialog Challenge (SDC) 2010.  ...  Inspired by the use of CF in recommendation systems, where a user's preference for a new item is assume to resemble that for similar items rated previously, we adapt the idea to predict user evaluations  ...  cooperativity of system actions (responses).  ... 
doi:10.1109/jstsp.2012.2229965 fatcat:w3ps5u7e5jg7zgjciahznbcyk4

MEDIA: a semantically annotated corpus of task oriented dialogs in French

Hélène Bonneau-Maynard, Matthieu Quignard, Alexandre Denis
2009 Language Resources and Evaluation  
The aim of the French MEDIA project was to define a protocol for the evaluation of speech understanding modules for dialog systems.  ...  Two semantic annotation levels are distinguished in this approach.  ...  Acknowledgments Thanks to Christelle Ayache, Frédéric Béchet, Laurence Devillers, Anne Kuhn, Fabrice Lefévre, Djamel Mostefa, Sophie Rosset and Jeanne Villaneau for their participation in the project.  ... 
doi:10.1007/s10579-009-9103-2 fatcat:v4u4huxf4vhxrfcizpyd25ubwm

Optimizing Dialog Strategies for Conversational Agents Interacting in AmI Environments [chapter]

David Griol, Javier Carbó, José Manuel Molina
2012 Ambient Intelligence - Software and Applications  
the situations already present in the initial corpus.  ...  The dialog model of this agent has been developed by means of a statistical methodology that automatically explores the dialog space and allows learning new enhanced dialog strategies from a dialog corpus  ...  Our Dialog Simulation Technique Our approach for acquiring a dialog corpus is based on the interaction of a user simulator and a conversational agent simulator [3] .  ... 
doi:10.1007/978-3-642-28783-1_12 dblp:conf/isami/GriolCM12 fatcat:iqfogrkq6zfapadad5ux3x23rm

A framework for improving error detection and correction in spoken dialog systems

David Griol, José Manuel Molina
2016 Soft Computing - A Fusion of Foundations, Methodologies and Applications  
We also contribute the practical application of the proposed technique for a dialog system acting as a customer support service.Our results show the appropriateness of our technique to correctly detect  ...  One of the main problems which must be considered during the interaction with a spoken conversational interface is the propagation of errors through the different modules in the system.  ...  Acknowledgements This work was supported in part by Projects MINECO TEC2012-37832-C02-01, CICYT TEC2011-28626-C02-02, CAM CONTEXTS (S2009/TIC-1485).  ... 
doi:10.1007/s00500-016-2290-z fatcat:icfwutyuafeplalq2l3w4sv33u

Example-based error recovery strategy for spoken dialog system

Cheongjae Lee, Sangkeun Jung, Donghyeon Lee, Gary Geunbae Lee
2007 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)  
Error handling has become an important issue in spoken dialog systems. We describe an example-based approach to detect and repair errors in an example-based dialog modeling framework.  ...  An empirical evaluation of the car navigation system shows that our approach is effective to the novice users for operating the spoken dialog system.  ...  Then, the system actions are correctly predicted and the system utterances are generated by a template-based natural language generation.  ... 
doi:10.1109/asru.2007.4430169 dblp:conf/asru/LeeJLL07 fatcat:5iksz5h6dbe5nnihpj6eigmuh4

Towards versatile conversations with data-driven dialog management and its integration in commercial platforms

Pablo Cañas, David Griol, Zoraida Callejas
2021 Journal of Computational Science  
However, designing the dialog model used by these interfaces to decide system responses is still a hard-to-accomplish task for complex conversational interactions.  ...  Various configurations for classification algorithms are assessed with two dialog corpora of different application domains, size, dimensionalities and set of possible system responses.  ...  Funding for open access charge: Universidad de Granada / CBUA.  ... 
doi:10.1016/j.jocs.2021.101443 fatcat:yvikqr2mjngnvikyeonrgbi3ke

A proposal for the development of adaptive spoken interfaces to access the Web

David Griol, José Manuel Molina, Zoraida Callejas
2015 Neurocomputing  
Our framework employs statistical models based on neural networks that take into account the history of the dialog up to the current dialog state in order to predict the user's intention and the next system  ...  Spoken dialog systems have been proposed as a solution to facilitate a more natural human machine interaction.  ...  The main weakness is that the responses generated may correspond well to the previous system action, but do not make sense in the larger context of the dialog.  ... 
doi:10.1016/j.neucom.2014.09.087 fatcat:rn2i47v55fhftnckc3g2ay6bvq

Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models [article]

Bing Liu, Ian Lane
2017 arXiv   pre-print
In this paper, we present a deep reinforcement learning (RL) framework for iterative dialog policy optimization in end-to-end task-oriented dialog systems.  ...  Popular approaches in learning dialog policy with RL include letting a dialog agent to learn against a user simulator.  ...  Response Generation We use a template-based NLG module to convert the agent outputs (system action, slot values, and KB entity values) to natural language format.  ... 
arXiv:1709.06136v1 fatcat:jv3qrel6yjebda3ubrvsfpbhke

Recent Advances and Challenges in Task-oriented Dialog System [article]

Zheng Zhang, Ryuichi Takanobu, Qi Zhu, Minlie Huang, Xiaoyan Zhu
2020 arXiv   pre-print
We believe that this survey, though incomplete, can shed a light on future research in task-oriented dialog systems.  ...  We also discuss three critical topics for task-oriented dialog systems: (1) improving data efficiency to facilitate dialog modeling in low-resource settings, (2) modeling multi-turn dynamics for dialog  ...  . • Ontology Integration A task-oriented dialog system has to query the knowledge base (KB) to retrieve some entities for response generation.  ... 
arXiv:2003.07490v3 fatcat:powcuixxargkbp57kpwmjict3y
« Previous Showing results 1 — 15 out of 5,986 results