The Tactical Language and Culture Training System (TLCTS) helps people quickly acquire functional skills in foreign languages and cultures. It includes interactive lessons that focus on particular communicative skills and interactive games that apply those skills. Heavy emphasis is placed on spoken communication: learners must learn to speak the foreign language to complete the lessons and play the games. It focuses on the language and cultural skills needed to accomplish particular types of tasks and gives learners rich, realistic opportunities to practice achieving those tasks.
Several TLCTS courses have been developed so far. Tactical Iraqi, Tactical Pashto, and Tactical French are in widespread use by U.S. marines and soldiers, and increasingly by military service members in other countries. Additional courses are being developed for use by business executives, workers for nongovernmental organizations, and high school and college students. While precise numbers are impossible to obtain (we do not control copies made by the U.S. government), over 40,000 and as many as 60,000 people have trained so far with TLCTS courses. More than 1000 people download copies of TLCTS courses each month, either for their own use or to set up computer language labs and redistribute copies to students. Just one training site, the military advisor training center at Fort Riley, Kansas, trains approximately 10,000 people annually.
Artificial intelligence technologies play multiple essential functions in TLCTS. Speech is the primary input modality, so automated speech recognition tailored to foreign language learners is essential. TLCTS courses are populated with "virtual humans" that engage in dialogue with learners. AI techniques are used to model the decision processes of the virtual humans and to support the generation of their behavior. This makes it possible to give learners extensive conversational practice. Learner modeling software continually monitors each learner's application of communication skills to estimate the learner's level of mastery of these skills. This helps instructors and training supervisors to monitor learners' progress and enables the software to guide learners to where they need to focus their training effort. Artificial intelligence is also integrated into the systems' content authoring tools, assisting content authors in the creation and validation of instructional content.
[FIGURE 1 OMITTED]
TLCTS courses are currently delivered on personal computers, equipped with headset microphones. Each course contains a set of interactive Skill Builder lessons, focusing on particular communicative skills. Figure 1 illustrates an exercise page from the Skill Builder of Encounters: Chinese Language and Culture, a college-level Chinese course being developed in collaboration with Yale University and Chinese International Publishing Group. The figure is an example of a minidialogue exercise where the learner practices a conversational turn in the target language. Here the learner must think of an appropriate way to say his name. His response, "Wo xing Li Dawei" (My family name is Li Dawei) exhibits a common mistake made by beginning language learners: to confuse the semantically similar words "xing" (family name is) and "jiao" (name is). A correct response would be "Wo jiao Li Dawei." The virtual tutor (bottom left) gave appropriate corrective feedback. The spoken conversational system recognized the utterance (bottom center), and was able to recognize the error in the utterance, so that the virtual tutor can respond accordingly. Note that in exercises there is no single correct answer: any utterance that correctly conveys the intended meaning will be accepted. Depending on the type of exercise, the system can give feedback on pronunciation, morphological and grammatical forms, cultural pragmatics, or word choice, as in this example.
[FIGURE 2 OMITTED]
Games play an essential role in TLCTS courses, providing essential practice opportunities. …