The major challenge in designing a discriminative learning algorithm for predicting structured data is to address the computational issues arising from the exponential size of the output space. Existing algorithms make different assumptions to ensure efficient, polynomial time estimation of model parameters. For several combinatorial structures, including cycles, partially ordered sets, permutations and other graph classes, these assumptions do not hold. In this thesis, we address the problem of designing learning algorithms for predicting combinatorial structures by introducing two new assumptions: (i) The first assumption is that a particular counting problem can be solved efficiently. The consequence is a generalisation of the classical ridge regression for structured prediction. (ii) The second assumption is that a particular sampling problem can be solved efficiently. The consequence is a new technique for designing and analysing probabilistic structured prediction models. These results can be applied to solve several complex learning problems including but not limited to multi-label classification, multi-category hierarchical classification, and label ranking.

RESTful services on the Web expose information through retrievable resource representations that represent self-describing descriptions of resources, and through the way how these resources are interlinked through the hyperlinks that can be found in those representations. This basic design of RESTful services means that for extracting the most useful information from a service, it is necessary to understand a service's representations, which means both the semantics in terms of describing a resource, and also its semantics in terms of describing its linkage with other resources. Based on the Resource Linking Language (ReLL), this paper describes a framework for how RESTful services can be described, and how these descriptions can then be used to harvest information from these services. Building on this framework, a layered model of RESTful service semantics allows to represent a service's information in RDF/OWL. Because REST is based on the linkage between resources, the same model can be used for aggregating and interlinking multiple services for extracting RDF data from sets of RESTful services.

We propose automatically learning probabilistic Hierarchical Task Networks (pHTNs) in order to capture a user's preferences on plans, by observing only the user's behavior. HTNs are a common choice of representation for a variety of purposes in planning, including work on learning in planning. Our contributions are (a) learning structure and (b) representing preferences. In contrast, prior work employing HTNs considers learning method preconditions (instead of structure) and representing domain physics or search control knowledge (rather than preferences). Initially we will assume that the observed distribution of plans is an accurate representation of user preference, and then generalize to the situation where feasibility constraints frequently prevent the execution of preferred plans. In order to learn a distribution on plans we adapt an Expectation-Maximization (EM) technique from the discipline of (probabilistic) grammar induction, taking the perspective of task reductions as productions in a context-free grammar over primitive actions. To account for the difference between the distributions of possible and preferred plans we subsequently modify this core EM technique, in short, by rescaling its input.

Paraphrasing methods recognize, generate, or extract phrases, sentences, or longer natural language expressions that convey almost the same information. Textual entailment methods, on the other hand, recognize, generate, or extract pairs of natural language expressions, such that a human who reads (and trusts) the first element of a pair would most likely infer that the other element is also true. Paraphrasing can be seen as bidirectional textual entailment and methods from the two areas are often similar. Both kinds of methods are useful, at least in principle, in a wide range of natural language processing applications, including question answering, summarization, text generation, and machine translation. We summarize key ideas from the two areas by considering in turn recognition, generation, and extraction methods, also pointing to prominent articles and resources.

Aiming at accurate recognition of relations, we introduce local alignment kernels and explore various possibilities of using them for this task. We give a definition of a local alignment (LA) kernel based on the Smith-Waterman score as a sequence similarity measure and proceed with a range of possibilities for computing similarity between elements of sequences. We show how distributional similarity measures obtained from unlabeled data can be incorporated into the learning task as semantic knowledge. Our experiments suggest that the LA kernel yields promising results on various biomedical corpora outperforming two baselines by a large margin. Additional series of experiments have been conducted on the data sets of seven general relation types, where the performance of the LA kernel is comparable to the current state-of-the-art results.

The Association for the Advancement of Artificial Intelligence was pleased to present the 2009 Fall Symposium Series, held Thursday through Saturday, November 5–7, at the Westin Arlington Gateway in Arlington, Virginia. The Symposium Series was preceded on Wednesday, November 4 by a one-day AI funding seminar. The titles of the seven symposia were as follows: (1) Biologically Inspired Cognitive Architectures, (2) Cognitive and Metacognitive Educational Systems, (3) Complex Adaptive Systems and the Threshold Effect: Views from the Natural and Social Sciences, (4) Manifold Learning and Its Applications, (5) Multirepresentational Architectures for Human-Level Intelligence, (6) The Uses of Computational Argumentation, and (7) Virtual Healthcare Interaction.

This article introduces the challenge of digital preservation in the area of engineering design and manufacturing and presents a methodology to apply knowledge representation and semantic techniques to develop Digital Engineering Archives. This work is part of an ongoing, multiuniversity, effort to create cyber infrastructure-based engineering repositories for undergraduates (CIBER-U) to support engineering design education. The technical approach is to use knowledge representation techniques to create formal models of engineering data elements, workflows and processes. With these formal engineering knowledge and processes can be captured and preserved with some guarantee of long-term interpretability. The article presents examples of how the techniques can be used to encode specific engineering information packages and workflows. These techniques are being integrated into a semantic wiki that supports the CIBER-U engineering education activities across nine universities and involving over 3500 students since 2006.

Over the past decade, we have been engaged in an extensive research effort to build virtual humans and applications that use them.  Building a virtual human might be considered the quintessential AI problem, because it brings together many of the key features, such as autonomy, natural communication, sophisticated reasoning and behavior, that distinguish AI systems.  This paper describes major virtual human systems we have built and important lessons we have learned along the way.

Series, held Thursday through Saturday, November 5-7, at he Association for the Advancement of Artificial Intelligence the Westin Arlington Gateway in Arlington, Virginia. The titles of the seven symposia were as follows: (1) Biologically Inspired Cognitive Biologically Inspired Cognitive Architectures Architectures, (2) Cognitive and Metacognitive Cognitive and Metacognitive Educational Systems Educational Systems, (3) Complex Adaptive Complex Adaptive Systems and the Threshold Effect: Views from the Natural Systems and the Threshold Effect: Views and Social Sciences from the Natural and Social Sciences, (4) Manifold Manifold Learning and Its Applications Learning and Its Applications, (5) Multirepresentational Architectures for Human-Level Multirepresentational Architectures for Human-Level Intelligence Intelligence, (6) The Uses of Computational The Uses of Computational Argumentation Argumentation, and (7) Virtual Healthcare Virtual Healthcare Interaction Interaction. An informal reception was held on Thursday, November 5. A general plenary session, in which the highlights of each symposium were presented, was held on Friday, November 6. The challenge of creating a real-life computational equivalent of the human mind requires that we better understand at a computational level how natural intelligent systems develop their cognitive and learning functions. They will behave, variety of disjoined communities and schools of learn, communicate, and "think" as conscious thought that used to speak different languages and beings in general, in addition to being able to perform ignore each other.

The poker AAAI membership is required for eligibility.