We assume that the brain is some kind of a computer and look at operations implied by the figurative use of language. Figurative language is pervasive, bypasses the literal meaning of what is said and is interpreted metaphorically or by analogy. Such an interpretation calls for a mapping in concept space, leading us to speculate about the nature of concept space in terms of readily computable mappings. We find that mappings of the appropriate kind are possible in high-dimensional spaces and demonstrate them with the simplest such space, namely, where the dimensions are binary. Two operations on binary vectors, one akin to addition and the other akin to multiplication, allow new representations to be composed from existing ones, and the ``multiplication'' operation is also suited for the mapping. The properties of high-dimensional spaces have been shown elsewhere to correspond to cognitive phenomena such as memory recall. The present ideas further suggest the suitability of high-dimensional representation for cognitive modeling.

TeamTalk is dialogue framework that supports multi-participant spoken interaction between humans and robots in a task-oriented setting that requires cooperation and coordination between team members. This paper describes some recently added features to the system, in particular the ability for robots to accept and remember location labels and the ability to learn action sequences. These capabilities reflect the incorporation into the system of an ontology and an instruction understanding component.

A promising application area for proactive assistant agents is automated tutoring and training.  Intelligent tutoring systems (ITSs) assist tutors and tutees by automating diagnosis and adaptive tutoring. These tasks are well modeled by a partially observable Markov decision process (POMDP) since it accounts for the uncertainty inherent in diagnosis. However, an important aspect of making POMDP solvers feasible for real-world problems is selecting appropriate representations for states, actions, and observations. This paper studies two scalable POMDP state and observation representations. State queues allow POMDPs to temporarily ignore less-relevant states. Observation chains represent information in independent dimensions using sequences of observations to reduce the size of the observation set. Preliminary experiments with simulated tutees suggest the experimental representations perform as well as lossless POMDPs, and can model much larger problems.

Coarse word sense disambiguation (WSD) is an NLP task that is both important and practical: it aims to distinguish senses of a word that have very different meanings, while avoiding the complexity that comes from trying to finely distinguish every possible word sense. Reasoning techniques that make use of common sense information can help to solve the WSD problem by taking word meaning and context into account. We have created a system for coarse word sense disambiguation using blending, a common sense reasoning technique, to combine information from SemCor, WordNet, ConceptNet and Extended WordNet. Within that space, a correct sense is suggested based on the similarity of the ambiguous word to each of its possible word senses. The general blending-based system performed well at the task, achieving an f-score of 80.8\% on the 2007 SemEval Coarse Word Sense Disambiguation task.

In this paper, we describe an evaluation of the impact of embodiment, the effect of different kinds of embodiment, and the benefits of different aspects of embodiment, on direction-giving systems. We compared a robot, embodied conversational agent (ECA), and GPS giving directions, when these systems used speaker-perspective gestures, listener-perspective gestures and no gestures. Results demonstrated that, while there was no difference in direction-giving performance between the robot and the ECA, and little difference in participants’perceptions, there was a considerable effect of the type of gesture employed, and several interesting interactions between type of embodiment and aspects of embodiment.

An account of the labels commonly used to express themes could both help in assessing the coverage of models of narrative processing, and support recognizing themes by the textual appearance of these labels. This paper presents a preliminary analysis and catalog of thematic labels such as “vicious cycle” and “underdog”. In contrast to a top-down approach characterizing themes in terms of components of a model of narrative processing, a bottom-up approach is taken. Thematic labels are gathered independent of any particular model and they are catalogued according to the types of relationships the corresponding themes convey.

A new architectural framework for a metacognitive tutoring system is presented that is aimed to stimulate self-regulatory behavior in the learner.The new framework extends the cognitive architecture of TutorJ that has been already proposed by some of the authors. TutorJ relies mainly on dialogic interaction with the user, and makes use of a statistical dialogue planner implemented through a Partially Observable Markov Decision Process (POMDP). A suitable two-level structure has been designed for the statistical reasoner to cope with measuring and stimulating metacognitive skills in the user. Suitable actions have been designed to this purpose starting from the analysis of the main questionnaires proposed in the literature. Our reasoner has been designed to model the relation between each item in a questionnaire and the related metacognitive skill, so the proper action can be selected by the tutoring agent. The complete framework is detailed, the reasoner structure is discussed, and a simple application scenario is presented.

The KNEXT system produces a large volume of factoids from text, expressing possibilistic general claims such as that 'A PERSON MAY HAVE A HEAD' or 'PEOPLE MAY SAY SOMETHING'. We present a rule-based method to sharpen certain classes of factoids into stronger, quantified claims such as 'ALL OR MOST PERSONS HAVE A HEAD' or 'ALL OR MOST PERSONS AT LEAST OCCASIONALLY SAY SOMETHING' -- statements strong enough to be used for inference. The judgement of whether and how to sharpen a factoid depends on the semantic categories of the terms involved and the strength of the quantifier depends on how strongly the subject is associated with what is predicated of it. We provide an initial assessment of the quality of such automatic strengthening of knowledge and examples of reasoning with multiple sharpened premises.

This paper proposes a number of social issues that are essential in understanding any given story, and thus, that must be included in a comprehensive approach to computational modeling of narrative. It focuses on oral narratives, and on the social event of the telling of a story. For participants in the telling, the central social issue is the story’s evaluation or meaning: the point or moral of the story. Value or meaning is created relative to social membership, and so, to understand evaluation, it is not sufficient to understand a story solely as a bounded unit. Therefore, this paper examines the ways in which narrative meaning is negotiated between narrator and interlocutors. It demonstrates how a given story can take on different meanings for different audiences. The life course of a story is also proposed as relevant dimension for understanding. Ephemeral stories are distinguished from stories which have multiple tellings, both for the stories of individuals, and for stories which form part of the story stock of institutions. Storytelling rights are also considered: who within a group has the right to tell a particular story on a particular occasion. These issues are proposed as potential meta-data to be used in the analysis of stories. Finally, the paper indicates an area in which computational understanding of narrative, including these social issues, has potential for practical applications: as part of current commercial knowledge capture and archiving activities.

The cardinal direction calculus (CDC) proposed by Goyal and Egenhofer is a very expressive qualitative calculus for directional information of extended objects. Early work has shown that consistency checking of complete networks of basic CDC constraints is tractable while reasoning with the CDC in general is NP-hard. This paper shows, however, if allowing some constraints unspecified, then consistency checking of possibly incomplete networks of basic CDC constraints is already intractable. This draws a sharp boundary between the tractable and intractable subclasses of the CDC. The result is achieved by a reduction from the well-known 3-SAT problem.