Tutorial Response Generation in a Writing Tool for Deaf Learners of English

ICICLE (Interactive Computer Identi cation and Correction of Language Errors) is a tutoring system under development that instructs deaf users of American Sign Language on written English skills. (See (McCoy & Masterman (Michaud) 1997) for a discussion of overall system architecture.) The text generation module it will employ produces original text to instruct the user on errors found in his or her writing, tailored to the user's understanding and learning style. The model I propose for planning this text composes it according to a four-tier response anatomy. It combines bottomup and top-down planning approaches and takes into account a detailed representation of user language prociency and a history of interaction with a user in order to create text that is maximally understandable and informative to the individual. The initial bottom-up part of the planning will employ a domain knowledge base containing information about the errors recognized by the system to cluster similar errors found in a piece of writing and to order those clusters according to guidelines directing the ow of a tutorial session. My work is concerned with the subsequent top-down phase which builds and eshes out a hierarchical text plan to tutor on an error. This phase employs a response anatomy which is comprised of content, method, form, and manner. Content refers to the error(s) to be discussed; the method is the choice between possible pedagogical approaches to discussing the error; the form is the determination of how to structure the approach de ned by the method; and the manner refers to cohesive factors involved in a contextuallyaware explanation. The top-down planning begins with the posting of the goal of instructing the user on an error and the selection of plan operators that represent approaches toward realizing this goal. My plan operator design is based largely on the work in (Moore &