In this paper a system was developed for robot behavior acquisition using kinesthetic demonstrations. It enables a humanoid robot to imitate constrained reaching gestures directed towards a target using a learning algorithm based on Gaussian Mixture Models. The imitation trajectory can be reshaped in order to satisfy the constraints of the task and it can adapt to changes in the initial conditions and to target displacements occurring during movement execution. The potential of this method was evaluated using experiments with the Nao, Aldebaran’s humanoid robot.

This paper describes a system called SITAC based on our proposed approach to discover concepts (called SITACs) in text archives that are identical semantically but alter their names over time. Our approach integrates natural language processing, association rule mining and contextual similarity to discover SITACs in order to answer historical queries over text corpora.

The ability to form object categories is an important milestone in human infant development (Cohen 2003). We propose a framework that allows a robot to form a unified object categorization from several interactions with objects. This framework is consistent with the principle that robot a) Drop Block b) Grasp c) Move learning should be ultimately grounded in the robot's perceptual and behavioral repertoire (Stoytchev 2009). This paper builds upon our previous work (Griffith et al. 2009) by adding more exploratory behaviors (now 6 instead of 1) and by employing consensus clustering for finding a single, unified object categorization. The framework was tested on a container/non-container categorization task with 20 objects.

The UMLS Metathesaurus was assembled by integrating its ancestors. We introduced an inconsistency definition for some 150 source vocabularies; it contains more than Metathesaurus concepts based on their hierarchical relations 2 million concepts (i.e., clusters of synonymous terms coming and compute all such inconsistent concepts. After that we from multiple source vocabularies identified by a Concept manually review some of the inconsistent concepts to determine Unique Identifier). The UMLS Metathesaurus contains the ones that have erroneous synonymy relations such also more than 36 million relations between these concepts, as wrong synonymy.

The selection of the action to do next is one of the central problems faced by autonomous agents. In AI, three approaches have been used to address this problem: the programming-based approach, where the agent controller is given by the programmer, the learning-based approach, where the controller is induced from experience via a learning algorithm, and the model-based approach, where the controller is derived from a model of the problem. Planning in AI is best conceived as the model-based approach to action selection. The models represent the initial situation, actions, sensors, and goals. The main challenge in planning is computational, as all the models, whether accommodating feedback and uncertainty or not, are intractable in the worst case. In this article, I review some of the models considered in current planning research, the progress achieved in solving these models, and some of the open problems.

Correcting recognition errors is often necessary in a speech interface. These errors not only reduce users' overall entry rate, but can also lead to frustration. While making fewer recognition errors is undoubtedly helpful, facilities for supporting user-guided correction are also critical. We explore how to better support user corrections using Parakeet — a continuous speech recognition system for mobile touch-screen devices. Parakeet's interface is designed for easy error correction on a handheld device. Users correct errors by selecting alternative words from a word confusion network and by typing on a predictive software keyboard. Our interface design was guided by computational experiments and used a variety of information sources to aid the correction process. In user studies, participants were able to write text effectively despite sometimes high initial recognition error rates. Using Parakeet as an example, we discuss principles we found were important for building an effective speech correction interface.

The bare minimum lexical resource required to translate between a pair of languages is a translation dictionary. Unfortunately, dictionaries exist only between a tiny fraction of the 49 million possible language-pairs making machine translation virtually impossible between most of the languages. This paper summarizes the last four years of our research motivated by the vision of panlingual communication. Our research comprises three key steps. First, we compile over 630 freely available dictionaries over the Web and convert this data into a single representation – the translation graph. Second, we build several inference algorithms that infer translations between word pairs even when no dictionary lists them as translations. Finally, we run our inference procedure offline to construct PANDICTIONARY– a sense-distinguished, massively multilingual dictionary that has translations in more than 1000 languages. Our experiments assess the quality of this dictionary and find that we have 4 times as many translations at a high precision of 0.9 compared to the English Wiktionary, which is the lexical resource closest to PANDICTIONARY.

Machine learning and data mining have become aware that using constraints when learning patterns and rules can be very useful. To this end, a large number of special purpose systems and techniques have been developed for solving such constraint-based mining and learning problems. These techniques have, so far, been developed independently of the general purpose tools and principles of constraint programming known within the field of artificial intelligence. This paper shows that off-the-shelf constraint programming techniques can be applied to various pattern mining and rule learning problems (cf. also (De Raedt, Guns, and Nijssen 2008; Nijssen, Guns, and De Raedt 2009)). This does not only lead to methodologies that are more general and flexible, but also provides new insights into the underlying mining problems that allow us to improve the state-of-the-art in data mining. Such a combination of constraint programming and data mining raises a number of interesting new questions and challenges.

This paper summarizes our line of research about the introduction of function symbols (functions) in Answer Set Programming (ASP) – a powerful language for knowledge representation and reasoning. The undecidability of reasoning on ASP with functions, implied that functions were subject to severe restrictions or disallowed at all, drastically limiting ASP applicability. We overcame most of the technical difficulties preventing this introduction, and we singled out a highly expressive class of programs with functions (FG-programs), allowing the (possibly recursive) use of function terms in the full ASP language with disjunction and negation. Reasoning on FG-programs is decidable, and they can express any computable function (causing membership in this class to be semi-decidable). We singled out also FD-programs, a subset of FG-programs which are effectively recognizable, while keeping the computability of reasoning. We implemented all results into the DLV system, thus obtaining an ASP system allowing to encode any computable function in a rich and fully declarative KRR language, ensuring termination on every FG program. Finally, we singled out the class of DFRP programs, where decidability of reasoning is guaranteed and Prolog-like functions are allowed.

Answering queries posed over knowledge bases is a central problem in knowledge representation and database theory. In the database area, checking query containment is an important query optimization and schema integration technique. In knowledge representation it has been used for object classification, schema integration, service discovery, and more. In the presence of a knowledge base, the problem of query containment is strictly related to that of query answering; indeed, the two are reducible to each other; we focus on the latter, and our results immediately extend to the former.