Clustering and visualization of large text document collections aids in browsing, navigation, and information retrieval. We present a document clustering and visualization method based on Latent Dirichlet Allocation and self-organizing maps (LDA-SOM). LDA-SOM clusters documents based on topical content and renders clusters in an intuitive two-dimensional format. Document topics are inferred using a probabilistic topic model. Then, due to the topology preserving properties of self-organizing maps, document clusters with similar topic distributions are placed near one another in the visualization. This provides the user an intuitive means of browsing from one cluster to another based on topics held in common. The effectiveness of LDA-SOM is evaluated on the 20 Newsgroups and NIPS data sets.

As robots become more common, it becomes increasingly useful for them to communicate and effectively share knowledge that they have learned through their individual experiences.  Learning from experiences, however, is often-times embodiment-specific; that is, the knowledge learned is grounded in the robot’s unique sensors and actuators.  This type of learning raises questions as to how communication and knowledge exchange via social interaction can occur, as properties of the world can be grounded differently in different robots.  This is especially true when the robots are heterogeneous, with different sensors and perceptual features used to define the properties.  In this paper, we present methods and representations that allow heterogeneous robots to learn grounded property representations, such as that of color categories, and then build models of their similarities and differences in order to map their respective representations.  We use a conceptual space representation, where object properties are learned and represented as regions in a metric space, implemented via supervised learning of Gaussian Mixture Models.  We then propose to use confusion matrices that are built using instances from each robot, obtained in a shared context, in order to learn mappings between the properties of each robot.  Results are demonstrated using two perceptually heterogeneous Pioneer robots, one with a web camera and another with a camcorder.

We present a semantically-driven approach to uncertainties within and across ontologies. Ontologies are widely used not only by the Semantic Web but also by artificial systems in general. They represent and structure a domain with respect to its semantics. Uncertainties, however, have been rarely taken into account in ontological representation, even though they are inevitable when applying ontologies in `real world' applications. In this paper, we analyze why uncertainties are necessary for ontologies, how and where uncertainties have to be represented in ontologies, and what their semantics are. In particular, we investigate which ontology constructions need to address uncertainty issues and which ontology constructions should not be affected by uncertainties on the basis of their semantics. As a result, the use of uncertainties is restricted to appropriate cases, which reduces complexity and guides ontology development. We give examples and motivation from the field of spatially-aware systems in indoor environments.

A neural net with multiple output nodes is capable of distinguishing among a set of related input classes even in the absence of training. It can do so with an accuracy that is markedly better than random guessing. This is because each class will tend to activate a different set of output nodes. We refer to this tendency as the net's 'inherent' bias. Ascertaining a net's inherent bias  may be thought of as learning the net. One may learn the net either instead of training it, or prior to training it. Furthermore, one only needs a small number of samples from each input class in order to reliably learn the net. If a net has been previously trained on a different, related set of classes, then ascertaining the inherent bias is a form of knowledge transfer. When such a net is trained to respond in accordance with its inherent bias, one may obtain substantially higher accuracies than is provided by nets trained in the standard fashion. Furthermore, when using a deep net, we were able to obtain such improvements while only allowing the top layer of the net to train. This layer contained only about 5.7% of the net's free parameters.

Knowledge compilation is a common technique for propositional logic knowledge bases. A given knowledge base is transformed into a normal form, for which queries can be answered efficiently. This precompilation step is expensive, but it only has to be performed once.  We apply this technique to knowledge bases defined  in the Description Logic ALC. We discuss an efficient satisfiability test as well as a subsumption test for precompiled concepts and Tboxes. Further we use the precompiled Tboxes for efficient Tbox reasoning. Finally we present first experimental results of our approach.

Many important tasks can be cast as weighted relational satisfiability problems.  Propositionalizing relational theories and making inferences with them using SAT algorithms has proven effective in many cases.  However, these approaches require that all objects in a domain be known in advance.  Many domains, from language understanding to machine vision, involve reasoning about objects that are not known beforehand.  Theories with unknown objects can require models with infinite objects in their domain and thus lead to propositionalized SAT theories that existing algorithms cannot deal with.  To address these problems, we characterize a class of relational generative weighted satisfiability theories (GenSAT) over potentially infinite domains and propose an algorithm, GenDPLL, for finding models of these theories.  We introduce the notion of a relevant model and an increasing cost theory to identify conditions under which GenDPLL is complete, even when a theory has infinite models.

Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), involve an iterative process of model optimization to identify different types of words or semantic entities. This optimization to achieve a more precise model becomes computationally difficult as the number of iterations increase. The small datasets available for training typically limit the models. Adding iterations on such sets to further optimize the model can often cause over-fitting, which generally leads to reduced performance. Therefore, the choice of convergence criteria is a critical step in robust and accurate model building. We evaluate different convergence criteria in terms of their robustness, stopping threshold selection, and independence from the training data size and entity. The underlying framework employs a limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) parameter optimization in the context of Conditional Random Fields (CRF). This paper presents a convergence criterion for robust training irrespective of semantic types and data sizes with two-orders of magnitude reduction in stopping threshold for improved model accuracy and faster convergence. Additionally, we examine convergence with active learning to further reduce the training data and training time.

Within a Question Answering (QA) framework, Question Context plays a vital role. We define Question Context to be background knowledge that can be used to represent the user’s information need more completely than the terms in the query alone. This paper proposes a novel approach that uses statistical language modeling techniques to develop a semantic Question Context which we then incorporate into the Information Retrieval (IR) stage of QA. Our approach proposes an Aspect-Based Relevance Language Model as basis of the Question Context Model. This model proposes that the sparse vocabulary of a query can be supplemented with semantic information from concepts (or aspects) related to query terms that already exist within the corpus. We incorporate the Aspect-Based Relevance Language Model into Question Context by first obtaining all of the latent concepts that exist in the corpus for a particular question topic. Then, we derive a likelihood of relevance that relates each Context Term (CT) associated with those aspects to the user’s query. Context Terms from the topics with the highest likelihood of relevance are then incorporated into the query language model based on their relevance score values. We use both query expansion and document model smoothing techniques and evaluate our approach using the traditional recall metric. Our results are promising and show significant improvements recall at low levels of precision using the query expansion method.

Conference and special track committees responsible for the 2009 FLAIRS conference.

List of officers of the FLAIRS society.