When general purpose software agents fail, it's often because they're brittle and need more background commonsense knowledge. In this paper we present relation properties as a valuable type of commonsense knowledge that can be automatically inferred at scale by reading the Web. People base many commonsense inferences on their knowledge of relation properties such as functionality, transitivity, and others. For example, all people know that bornIn(Year) satisfies the functionality property, meaning that each person can be born in exactly one year. Thus inferences like "Obama was born in 1961, so he was not born in 2008", which computers do not know, are obvious even to children. We demonstrate scalable heuristics for learning relation functionality from noisy Web text that outperform existing approaches to detecting functionality. The heuristics we use address Web NLP challenges that are also common to learning other relation properties, and can be easily transferred. Each relation property we learn for a Web-scale set of relations will enable computers to solve real tasks, and the data from learning many such properties will be a useful addition to general commonsense knowledge bases.

The paper focuses on how a model could be learnt for determining at runtime how much of spoken input needs to be understood, and what configuration of processes can be expected to yield that result. Typically, a dialogue system applies a fixed configuration of shallow and deep forms of processing to its input. The configuration tries to balance robustness with depth of understanding, creating a system that always tries to understand as well as it can. The paper adopts a different view, assuming that what needs to be understood can vary per context. To facilitate this any-depth processing, the paper proposes an approach based on learnable controllers. The paper illustrates the main ideas of the approach on examples from a robot acquiring situated dialogue competence, and a robot working with users on a task.

Computational Narrative has provided several examples of how to process narrations using semantical approaches. While many useful concepts for computational management of stories have been unveiled, a common barrier has hindered their development: semantic knowledge is still too complex to handle. In this paper, a focus shift based on narrative structure is proposed. Instead of digging deeper into the possibilities of semantic processing, analysing structural properties of stories and keeping the semantic load to a minimum can allow for a more efficient use of available narrative corpora, even without mimicking human behaviour.

Our learning by teaching environment has students take on the role and responsibilities of a teacher to a virtual student named Betty. The environment is structured so that successfully instructing their teachable agent requires the students to learn and understand science topics for themselves. This process is supported by adaptive scaffolding and feedback from the system. This feedback is instantiated through the interactions with the teachable agent and a mentor agent, named Mr. Davis. This paper provides an overview of two studies that were conducted with 5th grade science students and a description of the analysis techniques that we have developed for interpreting students’ activities in this learning environment.

The emergence of low-cost sensing architectures for diverse modalities has made it possible to deploy sensor networks that acquire large amounts of very high-dimensional data. To cope with such a data deluge, manifold models are often developed that provide a powerful theoretical and algorithmic framework for capturing the intrinsic structure of data governed by a low-dimensional set of parameters. However, these models do not typically take into account dependencies among multiple sensors. We thus propose a new joint manifold framework for data ensembles that exploits such dependencies. We show that joint manifold structure can lead to improved performance for manifold learning. Additionally, we leverage recent results concerning random projections of manifolds to formulate a universal, network-scalable dimensionality reduction scheme that efficiently fuses the data from all sensors.

Cochairs and Program Committee for the AAAI 2010 Symposium on Dialog with Robots.

In recent years, ConceptNet has gained notoriety in the Natural Language Processing (NLP) as a textual commonsense knowledge base (CSKB) for its utilization of k-lines (Liu and Sing, 2004a) which make it suitable for making practical inferences on corpora (Liu and Sing, 2004b). However, until now, ConceptNet has lacked support for many non-English languages. To alleviate this problem, we have implemented a software toolset for the Japanese Language that allows Japanese to be used with ConceptNet's concept inference system. This paper discusses the implementation of this toolset and a possible path for the development of toolsets in other languages with similar features.

Complex systems are found all around us. Companies, societies, fields who study these complex systems using the tools and markets, and humans rarely stay in a stable, predictable techniques of complex adaptive systems. We will explore state for long. Yet all these systems are characterized phenomena related to resilience, robustness, and evolvability by the notable persistence of some key attributes across various disciplines as one avenue towards exposing which maintain their identities, even as their constituent common dynamics that are found in these disparate domains. In the past, knowledge gained in each domain about these - What is it about these systems that define their identity?

A key concept in many Information Retrieval (IR) tasks, e.g. document indexing, query language modelling, aspect and diversity retrieval, is the relevance measurement of topics, i.e. to what extent an information object (e.g. a document or a query) is about the topics. This paper investigates the interference of relevance measurement of a topic caused by another topic. For example, consider that two user groups are required to judge whether a topic q is relevant to a document d, and q is presented together with another topic (referred to as a companion topic). If different companion topics are used for different groups, interestingly different relevance probabilities of q given d can be reached. In this paper, we present empirical results showing that the relevance of a topic to a document is greatly affected by the companion topic’s relevance to the same document, and the extent of the impact differs with respect to different companion topics. We further analyse the phenomenon from classical and quantum-like interference perspectives, and connect the phenomenon to nonreality and contextuality in quantum mechanics. We demonstrate that quantum like model fits in the empirical data, could be potentially used for predicting the relevance when interference exists.

The coagulation system (CS) is a complex, inter-connected biological system with major physiological and pathological roles. Adaptive mechanisms such as ubiquitous feedback and feedforward loops create non-linear relationships among its individual components and render the study of this biology at a molecular and cellular level nearly impossible. Computational modeling aims to overcome limitations of current analytical methods through in silico simulation of these complex interplays. We present herein an Agent Based Modeling and Simulation (ABMS) approach for simulating these complex interactions. Our ABMS approach utilizes a subset of 48 rules to define the interactions among 24 enzymes and factors of the CS. These rules simulate the interaction of each “agent”, such as substrates, enzymes, and cofactors, on a two-dimensional grid of ~3,000 cells and ~500,000 agents. Our ABMS method demonstrates the robustness of the physiologic CS system over large ranges of tissue factor (TF) concentrations. The system also demonstrates fragility as complete coagulation occurs at sufficiently high concentrations of TF. Removal of individual coagulation inhibitors from the physiologic system results in system fragility at relatively lower TF concentrations. The complete removal of coagulation inhibitors leads to a system that is incapable of controlling coagulation at all TF concentrations. The synergistic effects of the inhibitory pathways create an intricate regulatory mechanism that allows sufficient clot formation while preventing system wide activation of the CS; a robust system emerges.