Accession Number : ADA356902


Title :   The Military Language Tutor (MILT)


Descriptive Note : Final rept. 9 Apr 92-5 May 98


Corporate Author : ARMY RESEARCH INST FOR THE BEHAVIORAL AND SOCIAL SCIENCES ALEXANDRIA VA


Personal Author(s) : Kaplan, Jonathan D. ; Sabol, Mark A. ; Wisher, Robert A.


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a356902.pdf


Report Date : NOV 1998


Pagination or Media Count : 29


Abstract : MILT is a military foreign language tutor and an authoring system. MILT joins the strengths of previous computer based approaches to language training with emerging technologies from the fields of computational linguistics, computer science, and electrical engineering to form an innovative, interactive tutor in a Pentium based laptop computer. The first version of MILT with keyboard input was designed for Spanish and Arabic and can recognize tens of thousands of common words and hundreds of military terms in each of these languages. Its major software engine is a natural language processor (NLP). The goal of the MILT design team was an authoring system which would require no formal external training and which could be learned within four hours by anyone familiar with the Windows environment, even someone with no programming experience, using only documentation and internal MILT help functions. In MILT-DSR(discrete speech recognition), students are given an exercise which allows them to use language production to manipulate a graphics microworld. At Fort Campbell using 5th Special Forces Group personnel a field evaluation was conducted in early June, 1997. For each evaluation, two types of data were collected: (1) student attitudes toward the tutor and (2) instructional effects of the tutor.


Descriptors :   *COMPUTER AIDED INSTRUCTION , *HABITUATION LEARNING , *PSYCHOLINGUISTICS , ATTITUDES(PSYCHOLOGY) , PERFORMANCE(HUMAN) , HUMAN FACTORS ENGINEERING , MILITARY TRAINING , COMPUTATIONAL LINGUISTICS , NATURAL LANGUAGE , GRAPHICAL USER INTERFACE.


Subject Categories : LINGUISTICS


Distribution Statement : APPROVED FOR PUBLIC RELEASE