Improving question-answering with linking dialogues

ABSTRACT

Question-answering dialogue systems have found many applications in interactive learning environments. This paper is concerned with one such application for Army leadership training, where trainees input free-text questions that elicit pre-recorded video responses. Since these responses are already crafted before the question is asked, a certain degree of incoherence exists between the question that is asked and the answer that is given. This paper explores the use of short linking dialogues that stand in between the question and its video response to alleviate the problem of incoherence. We describe a set of experiments with human generated linking dialogues that demonstrate their added value. We then describe our implementation of an automated method for utilizing linking dialogues and show that these have better coherence properties than the original system without linking dialogues.

REFERENCES

• 1: Chih-Chung Chang, Chih-Jen Lin, LIBSVM: a library for support vector machines. 2001. http://www.csie.ntu.edu.tw/~cjlin/libsvm
• 2: Gandhe, S., Gordon A., Leuski A., Traum D., Oard D., First steps towards linking dialogues: mediating between free-text questions and pre-recorded video answers. Army Science Conference, 2004.
• 3: Graesser, A.C., Lang, K. L., and Roberts, R. M. Question answering in the context of stories. Journal of Experimental Psychology: General, (1991), 120(3).
• 4: Hill, R. J., Gordon, A., and Kim, J., Learning the lessons of leadership experience: Tools for interactive case method analysis. In Proceedings of the Twenty-fourth Army Science Conference, 2004.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.1 Applications and Expert Systems
          Subjects: Natural language interfaces

General Terms:
Algorithms

Keywords:
coherence, question-answering dialogue systems, training