KI 2012: Advances in Artificial Intelligence

This book constitutes the refereed proceedings of the 35th Annual German Conference on Artificial Intelligence, KI 2012, held in Saarbrücken, Germany, in September 2012.
The 19 revised full papers presented together with 9 short papers were carefully reviewed and selected from 57 submissions. The papers contain research results on theory and applicaiton of all aspects of AI.

Inhalt

Verification of Behaviour Networks Using Finite-State Automata.- Formal Semantics of Model Fields in Annotation-Based Specifications.- Searching with Partial Belief States in General Games with Incomplete Information.- A Machine-Learning Framework for Hybrid Machine Translation.-Using Equivalences of Worlds for Aggregation Semantics of Relational Conditionals.- Developing of a Multimodal Interactive Training System in Therapeutic Calisthenics for Elderly People.- PAC-Learning with General Class Noise Models.- Avoiding Moving Persons by Using Simple Trajectory Prediction and Spatio Temporal Planning.- Unsupervised Nearest Neighbors with Kernels.- A Compact Encoding of Pseudo-Boolean Constraints into SAT.- Small Talk Is More than Chit-Chat: Exploiting Structures of Casual Conversations for a Virtual Agent.- Clustering Based on Density Estimation with Sparse Grids.- A Comparison between Cognitive and AI Models of Blackjack Strategy Learning.- Plan Recognition by Program Execution in Continuous Temporal Domains.- Modeling Human Motion Trajectories by Sparse Activation of Motion Primitives Learned from Unpartitioned Data.- Nogoods in Qualitative Constraint-Based Reasoning.- Stochastic Gradient Descent with GPGPU.- Improved Query Suggestion by Query Search.- Knowledge-Base Revision Using Implications as Hypotheses.- Improving Confidence of Dual Averaging Stochastic Online Learning via Aggregation.- Supporting Fuzzy Metric Temporal Logic Based Situation Recognition by Mean Shift Clustering.- Ontology-Based Information Extraction for French Newspaper Articles.- Semantic Approach to Identity in Coreference Resolution Task.- Matching Points of Interest from Different Social Networking Sites.- Semi-analytic Natural Number Series Induction.- Dependency Parsing with Efficient Feature Extraction.- Strategies for Modelling Human Behaviour for Activity Recognition with Precondition-Effect Rules.- Gated Boosting: Efficient Classifier Boosting and Combining. Formal Semantics of Model Fields in Annotation-Based Specifications.- Searching with Partial Belief States in General Games with Incomplete Information.- A Machine-Learning Framework for Hybrid Machine Translation.-Using Equivalences of Worlds for Aggregation Semantics of Relational Conditionals.- Developing of a Multimodal Interactive Training System in Therapeutic Calisthenics for Elderly People.- PAC-Learning with General Class Noise Models.- Avoiding Moving Persons by Using Simple Trajectory Prediction and Spatio Temporal Planning.- Unsupervised Nearest Neighbors with Kernels.- A Compact Encoding of Pseudo-Boolean Constraints into SAT.- Small Talk Is More than Chit-Chat: Exploiting Structures of Casual Conversations for a Virtual Agent.- Clustering Based on Density Estimation with Sparse Grids.- A Comparison between Cognitive and AI Models of Blackjack Strategy Learning.- Plan Recognition by Program Execution in Continuous Temporal Domains.- Modeling Human Motion Trajectories by Sparse Activation of Motion Primitives Learned from Unpartitioned Data.- Nogoods in Qualitative Constraint-Based Reasoning.- Stochastic Gradient Descent with GPGPU.- Improved Query Suggestion by Query Search.- Knowledge-Base Revision Using Implications as Hypotheses.- Improving Confidence of Dual Averaging Stochastic Online Learning via Aggregation.- Supporting Fuzzy Metric Temporal Logic Based Situation Recognition by Mean Shift Clustering.- Ontology-Based Information Extraction for French Newspaper Articles.- Semantic Approach to Identity in Coreference Resolution Task.- Matching Points of Interest from Different Social Networking Sites.- Semi-analytic Natural Number Series Induction.- Dependency Parsing with Efficient Feature Extraction.- Strategies for Modelling Human Behaviour for Activity Recognition with Precondition-Effect Rules.- Gated Boosting: Efficient Classifier Boosting and Combining.