2001 — 2005 |
Franceschetti, Donald Graesser, Arthur [⬀] Garzon, Max (co-PI) [⬀] Person, Natalie Hu, Xiangen Wolff, Phillip Louwerse, Max (co-PI) [⬀] |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Developing Auto Tutor For Computer Literacy and Physics
The Tutoring Research Group at the University of Memphis has developed a computer tutor (called AutoTutor) that simulates the discourse patterns and pedagogical strategies of unaccomplished human tutors. The typical tutor in a school system is unaccomplished in the sense that the tutor has had no training in tutoring strategies and has only introductory-to-intermediate knowledge about the topic. The development of AutoTutor was funded by an NSF grant (SBR 9720314, in the Learning and Intelligent Systems program). The discourse patterns and pedagogical strategies in AutoTutor were based on a previous project that dissected 100 hours of naturalistic tutoring sessions.
AutoTutor is currently targeted for college students in introductory computer literacy courses, who learn the fundamentals of hardware, operating systems, and the Internet. Instead of merely being an information delivery system, AutoTutor serves as a discourse prosthesis or collaborative scaffold that assists the student in actively constructing knowledge. AutoTutor presents questions and problems from a curriculum script, attempts to comprehend learner contributions that are entered by keyboard, answers student questions, formulates dialog moves that are sensitive to the learner's contributions (such as short feedback, pumps, prompts, assertions, corrections, and hints), and delivers the dialog moves with a talking head. The talking head displays emotions, produces synthesized speech with discourse-sensitive intonation, and points to entities on graphical displays. AutoTutor has seven modules: a curriculum script, language extraction, speech act classification, latent semantic analysis (a statistical representation of domain knowledge), topic selection, dialog management, and a talking head. Evaluations of AutoTutor have shown that the tutoring system improves learning with an effect size that is comparable to typical human tutors in school systems, but not as high as accomplished human tutors and intelligent tutoring systems. The dialog moves of AutoTutor blend in the discourse context very smoothly because students cannot distinguish whether a speech act was generated by AutoTutor or a human tutor.
The proposed research will substantially expand the capabilities of AutoTutor by designing the discourse to handle more sophisticated tutoring mechanisms. These mechanisms should further enhance the active construction of knowledge. One enhancement is to get the student to articulate more knowledge, with more formal, symbolic, and precise specification; if the student doesn't say it, it is not considered covered by AutoTutor. Another enhancement is to set up the dialog so that it guides the user in manipulating a 3-dimensional microworld of a physical system; the student attempts to simulate a new state in the physical system by manipulating parameters, inputs, and formulae. The proposed research will develop AutoTutor in the domains of both computer literacy and Newtonian physics, so we will have some foundation for evaluating the generality of AutoTutor's mechanisms. AutoTutor has been designed to be generic, rather than domain-specific; an authoring tool will be developed that makes it easy for instructors to prepare new material on new topics. After the new versions of AutoTutor are completed, we will evaluate its effectiveness on learning gains, conversational smoothness, and pedagogical quality. During the course of achieving these engineering and educational objectives, the proposed project will conduct basic research in cognitive psychology, discourse processes, computer science, and computational linguistics. This research cuts across quadrant 2 (behavioral, cognitive, affective, and social aspects of human learning) and quadrant 3 (SMET learning in formal and informal educational settings).
|
1 |
2004 — 2008 |
Graesser, Arthur (co-PI) [⬀] Steedman, Mark Hu, Xiangen Louwerse, Max [⬀] Bard, Ellen (co-PI) [⬀] |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Tracking Multimodal Communication in Humans and Agents
TRACKING MULTIMODAL COMMUNICATION IN HUMANS AND AGENTS
This project investigates multimodal communication in humans and agents, focusing on two linguistic modalities - prosody and dialog structure, which reflect major communicative events, and three non-linguistic modalities - eye gaze, facial expressions, and body posture. It aims to determine 1. which of the non-linguistic modalities align with events marked by prosody and dialogue structure, and with one another; 2. whether, and if so when, these modalities are observed by the interlocutor; 3. whether the correct use of these channels actually aids the interlocutor's comprehension. Answers to these questions should provide a better understanding of the use of communicative resources in discourse and can subsequently aid the development of more effective animated conversational agents.
The outcomes of our observations will be modeled on controlled elicited dialog. To assure robust information on the interplay of modalities, we control the base conditions, genre, topic, and goals of unscripted dialogs. An ideal task for this is the Map Task, where dialog participants work together to reproduce on one player's map a route preprinted on the other's. The two maps, however, are slightly different, so that each player holds information important to the other. This scenario triggers a highly interactive, incremental and multimodal conversation.
In the proposed project a basic corpus of Map Task dialogues will be collected while recording spoken language, posture, facial expressions, and eye gaze. Hand gestures, discouraged by the task, will be recorded where they occur. These findings will be used in the Behavior Expression Animation Toolkit (BEAT) in order to augment the current intelligent system AutoTutor. AutoTutor has been developed for a broad range of tutoring environments that coach the student in following an expected set of descriptions or explanations. The coach-follower roles in the Map Task scenario make it possible to easily change the scenario for AutoTutor. In a series of usability experiments interactions of dialog participants with AutoTutor will be recorded. These experiments allow us to record not only the participant's impressions, but also his or her efficiency (the time to complete map, latency to find named objects, deviation of the instruction follower's drawn route from the instruction giver's model), and communicative behavior (discourse structure, gaze, facial expressions, etc.).
The research resulting from this project will benefit a large variety of fields, including cognitive science, computational linguistics, artificial intelligence, and computer science. In addition, the integration of the modalities into a working model will advance the development and use of intelligent conversational systems.
|
1 |
2006 — 2010 |
Batchelder, William Hu, Xiangen |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Multinomial Processing Tree Model: New Projects and Implementations
The project will develop new mathematical and statistical properties as well as computational software for a popular class of parametric statistical models for categorical data called multinomial processing tree (MPT) models. These models are used to measure an individual's ability to perform specific cognitive processes in a variety of experimental situations in the social and behavioral sciences. MPT models compute category probabilities from a parameterized tree structure, where individual parameters correspond to the success or failure probabilities of particular cognitive processes modeled to underlie the behavior in the situation. The project involves four main areas of work. The first area is to develop a new framework for representing tree models based on recursive definitions. This framework draws on the fact that any MPT model is itself a probabilistic mixture of other MPT models. Formulating MPT models with recursive axioms is designed to facilitate the statement and proofs of new theorems about their structure. The second area involves relating MPT models to other popular classes of models for categorical data. MPT models are structurally quite different than traditional additive models such as log-linear and logit models, and these differences lead to new ways to model cross classified data that are in the form of contingency tables. The third area of work is to develop new statistical inference for MPT models under realistic sampling conditions. In particular, standard Bayesian and classical Monte Carlo resampling approaches will be developed under the assumptions of small samples of observations governed by random variation in the parameter values. Bayesian hierarchical models for the entire MPT class will be developed by representing parameter variation as additive over participants and items as in the Rasch model from psychometric test theory. The final area of work is to construct a user friendly and accessible computational software package for MPT models that encompasses the new developments in the first three areas of the project. The results of the project are expected to lead to both a deeper understanding and a wider applicability of MPT models in the social and behavioral sciences.
Fundamentally, MPT models are useful as tools to measure the strength of underlying cognitive skills behind performance in cognitive and social tasks. For example successful performance in a memory experiment may involve initial successful attention, memory storage, memory organization, and subsequent memory retrieval; however successful performance can also result from the failure of any of these processes coupled with appropriate inferences or guessing tendencies. Earlier statistical work with MPT models was predicated on the availability of large data samples taken from a homogeneous pool of participants each of whom generates a sample of independent and identically distributed observations. More recently, MPT models are being used to measure the strength of specific cognitive abilities in special populations (e.g. schizophrenics, those affected with Alzheimer's disease, gifted children). Such situations usually involve heterogeneous participants where each participant generates only a small sample of observations. Thus, it is important to develop the mathematical and statistical properties of MPT models to deal with situations where these weaker sampling conditions apply. In this way, MPT models can be employed as measurement tools to pinpoint specific types of cognitive enhancement or cognitive decline due to such variables as education, drugs, disease, aging, and the like.
|
1 |