Filters








2,212 Hits in 2.6 sec

Probabilistic Dialogue Models for Dynamic Ontology Mapping [chapter]

Paolo Besana, Dave Robertson
2008 Lecture Notes in Computer Science  
doi:10.1007/978-3-540-89765-1_3 fatcat:lji46zvzbrfwtl3uqziv4k34nq

Techniques of Ontology and its Usage in Indian Languages - A Review

Rajveer Kaur, Saurabh Sharma
2015 International Journal of Computer Applications  
It is hereby concluded from the review that in Indian languages usage of ontology is very less because of the challenges to build ontology for minority languages.  ...  From the last few decades, different ontology building approaches are being used to build ontology either semi-automatically or automatically.  ...  The main focus is on scalable algorithms for answering threshold queries to probabilistic guarded Datalog+/− ontologies.  ... 
doi:10.5120/19975-1873 fatcat:klt7q4x4qff25mtjvoecrsgtuy

Computational system biology

Ankit Geete, Ankit Geete
2012 Nature Precedings  
 24 Saga bionetwork Building Disease Maps Data Repository Commons Pilots Discovery Platform 25  Data handling Network inference  Deep curation  Dynamical simulation  Model analysis  ...   Dynamical simulation  Model analysis 34 Deep curation • An alternative to data-driven network inference • The deep curation approach creates a detailed molecular interaction map by information  ...  integration of these tools are necessary to increase the capability of scientist to explore more and more biological systems • Require innovative idea to make this system biology more easy and comfortable for  ... 
doi:10.1038/npre.2012.7104.1 fatcat:bjpfdz3l25arndtlyeiqpiwhjm

Computational system biology

Ankit Geete, Ankit Geete
2012 Nature Precedings  
 24 Saga bionetwork Building Disease Maps Data Repository Commons Pilots Discovery Platform 25  Data handling Network inference  Deep curation  Dynamical simulation  Model analysis  ...   Dynamical simulation  Model analysis 34 Deep curation • An alternative to data-driven network inference • The deep curation approach creates a detailed molecular interaction map by information  ...  integration of these tools are necessary to increase the capability of scientist to explore more and more biological systems • Require innovative idea to make this system biology more easy and comfortable for  ... 
doi:10.1038/npre.2012.7104 fatcat:kup7lygoizet7jwp6b6dlh3f7a

Emergent Semantics Principles and Issues [chapter]

Karl Aberer, Philippe Cudré-Mauroux, Aris M. Ouksel, Tiziana Catarci, Mohand-Said Hacid, Arantza Illarramendi, Vipul Kashyap, Massimo Mecella, Eduardo Mena, Erich J. Neuhold, Olga De Troyer, Thomas Risse (+6 others)
2004 Lecture Notes in Computer Science  
Again, we hope for global properties to emerge from a multiplicity of pair-wise, local interactions, resulting eventually in a self-stabilizing semantic infrastructure.  ...  This implies for the schemas and classifications a more dynamic handling of the mappings.  ...  [31] uses machine-generated ontologies extracted from web forms to integrate web services. In [1] a probabilistic framework for reasoning with assertions on schema relationships is introduced.  ... 
doi:10.1007/978-3-540-24571-1_2 fatcat:pgon6yxlqvaprncn46x3xtux5u

UMIS: A Service for User Model Interoperability

Federica Cena, Roberto Furnari
2012 Advances in Internet of Things  
The goal is to support the process of interoperability in three ways: providing an efficient centralized discovery service; offering a service for simple interaction for the exchange of UM value in a p2p  ...  FURNARI 92  Parameters, the goals of the game; 1 To impose a common knowledge model is not always possible, since it is not easy to find a unique complete knowledge model with all the features of the  ...  However, other moda f ontology mapping c d be easily included in the work.  ... 
doi:10.4236/ait.2012.24012 fatcat:3irtdotl6zfdzjhspkopndifv4

Combining ITS and eLearning Technologies: Opportunities and Challenges [chapter]

Christopher Brooks, Jim Greer, Erica Melis, Carsten Ullrich
2006 Lecture Notes in Computer Science  
Both types of systems have strengths and weaknesses -ITSs are typically domain specific and rely on concise knowledge modeling and learner modeling, while eLearning systems are deployable in a wide range  ...  This paper provides possibilities for convergence of these two areas, and describes two of our experiences in providing an ITS-style approach to eLearning systems.  ...  The authors are solely responsible for its content.  ... 
doi:10.1007/11774303_28 fatcat:q3zumfy2pfayrcznam6g4wluzm

A hybrid approach to dialogue management based on probabilistic rules

Pierre Lison
2015 Computer Speech and Language  
We present a new modelling framework for dialogue management based on the concept of probabilistic rules.  ...  Probabilistic rules are defined as structured mappings between logical conditions and probabilistic effects.  ...  Kruijff, Kristiina Jokinen, Verena Rieser and Andrei Popescu-Belis for many useful comments.  ... 
doi:10.1016/j.csl.2015.01.001 fatcat:5j67rdwmvfdh5jkbsieoecqnou

Belief modelling for situation awareness in human-robot interaction

Pierre Lison, Carsten Ehrler, Geert-Jan M. Kruijff
2010 19th International Symposium in Robot and Human Interactive Communication  
Key to our approach is the use of Markov Logic as a unified framework for inference over these beliefs. Markov Logic is a combination of first-order logic and probabilistic graphical models.  ...  The approach is being integrated into a cognitive architecture for mobile robots interacting with humans using spoken dialogue.  ...  Typical HRI environments are challenging to model, being simultaneously complex, multi-agent, dynamic and uncertain.  ... 
doi:10.1109/roman.2010.5598723 dblp:conf/ro-man/LisonEK10 fatcat:ou7d6kp4svgwjpawpn7ls3ruwu

Unsupervised Learning and Modeling of Knowledge and Intent for Spoken Dialogue Systems

Yun-Nung Chen
2015 Proceedings of the ACL-IJCNLP 2015 Student Research Workshop  
In the field of dialogue modeling, the partially observable Markov decision process (POMDP) model is a popular technique for dialogue management [164, 172] , reducing the cost of handcrafted dialogue  ...  Ontology induction maps observed surface patterns to semantic slot candidates. Word relation model constructs correlations between surface patterns.  ... 
doi:10.3115/v1/p15-3001 dblp:conf/acl/Chen15 fatcat:kfxqwlfgpfgl7maz25j42nebme

Interfacing language, spatial perception and cognition in Type Theory with Records

Simon Dobnik, Robin Cooper
2017 Journal of Language Modelling  
of a formal semantic theory and its practical implementations in situated dialogue agents.  ...  Keywords: spatial language, Type Theory with Records (TTR), computational framework We argue that computational modelling of perception, action, language, and cognition introduces several requirements  ...  The ontology capturing this knowledge may be static or dynamically built through interaction (Dobnik and Kelleher 2016) .  ... 
doi:10.15398/jlm.v5i2.148 fatcat:h22gjwyeq5befclfeh4jbiqvg4

Large-scale semantic mapping and reasoning with heterogeneous modalities

Andrzej Pronobis, Patric Jensfelt
2012 2012 IEEE International Conference on Robotics and Automation  
This paper presents a probabilistic framework combining heterogeneous, uncertain, information such as object observations, shape, size, appearance of rooms and human input for semantic mapping.  ...  A probabilistic graphical model, a chaingraph, is used to represent the conceptual information and perform spatial reasoning.  ...  and probabilistic generative models for data of lower dimensionality or conceptual knowledge).  ... 
doi:10.1109/icra.2012.6224637 dblp:conf/icra/PronobisJ12 fatcat:lltanixi2rhj7jr56ow7yev5si

Hybrid Control for Embodied Agents Applications [chapter]

Jan Miksatko, Michael Kipp
2009 Lecture Notes in Computer Science  
This allows us to choose the most appropriate method for each of the various behavioral processes, e.g. state charts for deliberative processes and rules for reactive behaviors.  ...  We propose a hybrid and modular approach to modeling the agent's control, combining state charts and rule processing.  ...  We would also like to thank to Charamel GmbH for providing us with their Avatar engine.  ... 
doi:10.1007/978-3-642-04617-9_66 fatcat:qbt55sgsg5bgxdl6twjouoyqna

Neural Belief Tracker: Data-Driven Dialogue State Tracking [article]

Nikola Mrkšić and Diarmuid Ó Séaghdha and Tsung-Hsien Wen and Blaise Thomson and Steve Young
2017 arXiv   pre-print
This is due to their dependency on either: a) Spoken Language Understanding models that require large amounts of annotated training data; or b) hand-crafted lexicons for capturing some of the linguistic  ...  NBT models reason over pre-trained word vectors, learning to compose them into distributed representations of user utterances and dialogue context.  ...  Acknowledgements The authors would like to thank Ivan Vulić, Ulrich Paquet, the Cambridge Dialogue Systems Group and the anonymous ACL reviewers for their constructive feedback and helpful discussions.  ... 
arXiv:1606.03777v2 fatcat:zdkzrbenqjct3ptaudgun3ph64

Neural Belief Tracker: Data-Driven Dialogue State Tracking

Nikola Mrkšić, Diarmuid Ó Séaghdha, Tsung-Hsien Wen, Blaise Thomson, Steve Young
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
This is due to their dependency on either: a) Spoken Language Understanding models that require large amounts of annotated training data; or b) hand-crafted lexicons for capturing some of the linguistic  ...  NBT models reason over pre-trained word vectors, learning to compose them into distributed representations of user utterances and dialogue context.  ...  Acknowledgements The authors would like to thank Ivan Vulić, Ulrich Paquet, the Cambridge Dialogue Systems Group and the anonymous ACL reviewers for their constructive feedback and helpful discussions.  ... 
doi:10.18653/v1/p17-1163 dblp:conf/acl/MrksicSWTY17 fatcat:ocz7x4ezdzbfrpff4oorycygba
« Previous Showing results 1 — 15 out of 2,212 results