Open Mind Common Sense (OMCS) is a freely available crowd-sourced knowledge base of natural language statements about the world. The goal of Open Mind Common Sense is to provide intuition to AI systems and applications by giving them access to a broad collection of basic information and the computational tools to work with this data. For our system demo, we will be presenting three aspects of the OMCS project: the OMCS knowledge base, the Concept-Net semantic network (Liu and Singh 2004) (Havasi, Speer, and Alonso 2007), and the AnalogySpace algorithm (Speer, Havasi, and Lieberman 2008) which deals well with noisy, user-contributed data. Figure 1: AnalogySpace discovers patterns in common sense Open Mind Common Sense takes a distributed approach knowledge and uses them for inference. The project allows the general public to enter commonsense score to indicate its reliability, which increases either when knowledge into it, without requiring any knowledge a contributor votes for a statement through our Web site of linguistics, artificial intelligence, or computer science.The or when multiple contributors submit equivalent statements OMCS has been collecting commonsense statements from independently.

Many social Web sites allow users to annotate the content with descriptive metadata, such as tags, and more recently also to organize content hierarchically. These types of structured metadata provide valuable evidence for learning how a community organizes knowledge. For instance, we can aggregate many personal hierarchies into a common taxonomy, also known as a folksonomy, that will aid users in visualizing and browsing social content, and also to help them in organizing their own content. However, learning from social metadata presents several challenges: sparseness, ambiguity, noise, and inconsistency. We describe an approach to folksonomy learning based on relational clustering that addresses these challenges by exploiting structured metadata contained in personal hierarchies. Our approach clusters similar hierarchies using their structure and tag statistics, then incrementally weaves them into a deeper, bushier tree. We study folksonomy learning using social metadata extracted from the photo-sharing site Flickr. We evaluate the learned folksonomy quantitatively by automatically comparing it to a reference taxonomy. Our empirical results suggest that the proposed framework, which addresses the challenges listed above, improves on existing folksonomy learning methods.

In this paper we explore challenges related to the engineering of plan libraries for plan recognition. This is an often overlooked problem, yet essential in the design of any real world plan recognizers. We mainly discuss challenges related to the evaluation of equivalence between plan libraries. We explain why this is a potential source of ill-conceived plan libraries. We consider an existing well-established probabilistic plan recognizer as vehicle for our discussion, using the formalism of probabilistic hierarchical task networks to represent plans. We propose avenues for exploring solutions to those challenges within that framework.

One major challenge of implementing a metacognitive architecture lies in its scalability and flexibility. We postulate that the difference between a reasoner and a metareasoner need not extend beyond what inputs they take, and we envision a network made of many instances of a few types of simple but powerful reasoning units to serve both roles. In this paper, we present a vision and motivation for such a framework with reusable, robust, and scalable components. This framework, called Scruffy Metacognition , is built on a symbolic representation that lends itself to processing using dimensionality reduction and principal component analysis. We discuss the components of such as system and how they work together for metacognitive reasoning. Additionally, we discuss evaluative tasks for our system focusing on social agent role-playing and object classification.

Traditionally, in the fields of artificial intelligence and robotics, representations of the self have been conspicuously absent. Capabilities of systems are listed explicitly by developers during construction and choices between behavioral options are decided based on search, inference, and planning. In robotics, while knowledge of the external world has often been acquired through experience, knowledge about the robot itself has generally been built in by the designer. Built-in models of the robot's kinematics, physical and sensory capabilities, and other equipment have stood in the place of self-knowledge, but none of these representations offer the flexibility, robustness, and functionality that are present in people. In this work, we seek to emulate forms of self-awareness developed during human infancy in our humanoid robot, Nico. In particular, we are interested in the ability to reason about the robot's embodiment and physical capabilities, with the robot building a model of itself through its experiences.

We present a game-theoretic model that formalizes core ideas of conversational grounding theory. This game-theoretic model is based on the concept of signaling games, originally proposed as a model of linguistic convention. We extend signaling games with an observation model, which allows for the possibility that the actions a dialog participant takes may only be partially observable to others. We then apply this model to the domain of referential communication tasks, a type of task commonly used in psycholinguistic experiments.

We present an AI called Visuo that guesses quantitative visuospatial magnitudes (e.g., heights, lengths) given adjective-noun pairs as input (e.g., “big hat”). It uses a database of tagged images as memory and infers unexperienced magnitudes by analogy with semantically-related concepts in memory. We show that transferring width-height ratios from a semantically-related concept yields significantly lower error rates than using dissimilar concepts when predicting the width-height ratios of novel inputs.

Reasoning by the usage of mental images has been the subject of much debate in Cognitive Science, especially among the schools of depictive and descriptive imagistic representations. Whether or not reasoning with mental images involves a mechanism or a process different from language based reasoning is an important question. This paper proposes that any theory which aims for a cohesive whole needs to be constrained by neurophysiological data and such data can be obtained by the Clock Drawing Test. The Clock Drawing Test (CDT) is a screening tool for cognitive impairment and can be used as a tool to test resilience of certain factors of visual spatial representations. Thus, it can help to form an empirical case for which factors are prone to debility and which factors are not during the onset and progress of cognitive impairment from a mental representation point of view. This paper presents 50 CDT tests done on patients with cognitive impairment and analyses the results which support the case for a depictive rather than a descriptive theory for imagistic representations. Lastly, this paper proposes that there is some evidence for a more dynamic and distributed nature of representation in the observations which question the above dichotomy and can be partly explained by certain aspects of the connectionist school of thought.

The architectural approach to AI focuses on the fixed structure underlying intelligence. Applying it to statistical relational AI should further stimulate the application of statistical relational techniques across AI, while focusing research on their commonalities, (in)compatibilities and integration. It could also yield new architectures that are simpler yet more comprehensive than today’s best.

This paper investigates how readily an unsolvable constraint satisfaction problem can be reformulated so that it becomes solvable. We investigate small changes in the definitions of the problemís constraints, changes that alter neither the structure of its constraint graph nor the tightness of its constraints. Our results show that structured and unstructured problems respond differently to such changes, as do easy and difficult problems taken from the same problem class. Several plausible explanations for this behavior are discussed.