Maxim Makatchev

The Architecture of Why2-Atlas: A Coach for Qualitative Physics Essay Writing

The Why2-Atlas system teaches qualitative physics by having students write paragraph-long explanations of simple mechanical phenomena. The tutor uses deep syntactic analysis and abductive theorem proving to convert the students essay to a proof. The proof formalizes not only what was said, but the likely beliefs behind what was said. This allows the tutor to uncover misconceptions as well as to detect missing correct parts of the explanation. If the tutor finds such a flaw in the essay, it conducts a dialogue intended to remedy the missing or misconceived beliefs, then asks the student to correct the essay. It often takes several iterations of essay correction and dialogue to get the student to produce an acceptable explanation. Pilot subjects have been run, and an evaluation is in progress. After explaining the research questions that the system addresses, the bulk of the paper describes the systems architecture and operation.

Human-robot interface using agents communicating in an XML-based markup language

The paper concerns an agent-based human-robot interface via the Internet. A user client and an embedded software are viewed as agents with limited computational and communication resources. To facilitate the communication between the real-time embedded agents and the user interface agents via the communication channel of uncertain quality the proxy agent is proposed as a mediator. The functions assigned to the proxy agent target reduction of inter-agent communication load and minimization of computational resources taken by the embedded agents and user interface agents for communication-related tasks. An XML-based language, RoboML, is designed to serve as a common language for robot programming, agent communication and knowledge representation. The human-robot interface software prototype is developed for an autonomous guided vehicle to evaluate the proposed techniques.

Combining Competing Language Understanding Approaches in an Intelligent Tutoring System

When implementing a tutoring system that attempts a deep understanding of students’ natural language explanations, there are three basic approaches to choose between; symbolic, in which sentence strings are parsed using a lexicon and grammar; statistical, in which a corpus is used to train a text classifier; and hybrid, in which rich, symbolically produced features supplement statistical training. Because each type of approach requires different amounts of domain knowledge preparation and provides different quality output for the same input, we describe a method for heuristically combining multiple natural language understanding approaches in an attempt to use each to its best advantage. We explore two basic models for combining approaches in the context of a tutoring system; one where heuristics select the first satisficing representation and another in which heuristics select the highest ranked representation.

Believable Robot Characters

� Believability of characters has been an objective in literature, theater, film, and animation. We argue that believable robot characters are important in human-robot interaction, as well. In particular, we contend that believable characters evoke users’ social responses that, for some tasks, lead to more natural interactions and are associated with improved task performance. In a dialogue-capable robot, a key to such believability is the integration of a consistent story line, verbal and nonverbal behaviors, and sociocultural context. We describe our work in this area and present empirical results from three robot receptionist test beds that operate “in the wild.”

Expressing ethnicity through behaviors of a robot character

Achieving homophily, or association based on similarity, between a human user and a robot holds a promise of improved perception and task performance. However, no previous studies that address homophily via ethnic similarity with robots exist. In this paper, we discuss the difficulties of evoking ethnic cues in a robot, as opposed to a virtual agent, and an approach to overcome those difficulties based on using ethnically salient behaviors. We outline our methodology for selecting and evaluating such behaviors, and culminate with a study that evaluates our hypotheses of the possibility of ethnic attribution of a robot character through verbal and nonverbal behaviors and of achieving the homophily effect.

Relating initial turns of human-robot dialogues to discourse

User models can be useful for improving dialogue management. In this paper we analyze human-robot dialogues that occur during uncontrolled interactions and estimate relations between the initial dialogue turns and patterns of discourse that are indicative of such user traits as persistence and politeness. The significant effects shown in this preliminary study suggest that initial dialogue turns may be useful in modeling a users interaction style.

Understanding Complex Natural Language Explanations in Tutorial Applications

We describe the Why2-Atlas intelligent tutoring system for qualitative physics that interacts with students via natural language dialogue. We focus on the issue of analyzing and responding to multi-sentential explanations. We explore an approach that combines a statistical classifier, multiple semantic parsers and a formal reasoner for achieving a deeper understanding of these explanations in order to provide appropriate feedback on them.

Modeling Students’ Reasoning About Qualitative Physics: Heuristics for Abductive Proof Search

We describe a theorem prover that is used in the Why2-Atlas tutoring system for the purposes of evaluating the correctness of a student’s essay and for guiding feedback to the student. The weighted abduction framework of the prover is augmented with various heuristics to assist in searching for a proof that maximizes measures of utility and plausibility. We focus on two new heuristics we added to the theorem prover: (a) a specificity-based cost for assuming an atom, and (b) a rule choice preference that is based on the similarity between the graph of cross-references between the propositions in a candidate rule and the graph of cross-references between the set of goals. The two heuristics are relevant to any abduction framework and knowledge representation that allow for a metric of specificity for a proposition and cross-referencing of propositions via shared variables.

Incorporating a user model to improve detection of unhelpful robot answers

Dialogues with robots frequently exhibit social dialogue acts such as greeting, thanks, and goodbye. This opens the opportunity of using these dialogue acts for dialogue management, in particular for detecting misunderstandings. Our corpus analysis shows that the social dialogue acts have different scopes of their associations with the discourse features within the dialogue: greeting in the users first turn is associated with such distant, or global, features as the likelihood of having questions answered, persistence, and ending with bye. The users thanks turn, on the other hand, is strongly associated with the helpfulness of the preceding robots answer. We therefore interpret the greeting as a component of a user model that can provide information about the users traits and be associated with discourse features at various stages of the dialogue. We conduct a detailed analysis of the users thanking behavior and demonstrate that users thanks can be used in the detection of unhelpful robots answers. Incorporating the greeting information further improves the detection. We discuss possible applications of this work for human-robot dialogue management.