ABSTRACT
In this paper we describe the analytic question answering system HITIQA (High-Quality Interactive Question Answering) which has been developed over the last 2 years as an advanced research tool for information analysts. HITIQA is an interactive open-domain question answering technology designed to allow analysts to pose complex exploratory questions in natural language and obtain relevant information units to prepare their briefing reports. The system uses novel data-driven semantics to conduct a clarification dialogue with the user that explores the scope and the context of the desired answer space. The system has undergone extensive hands-on evaluations by a group of intelligence analysts. This evaluation validated the overall approach in HITIQA but also exposed limitations of the current prototype.
- Allen, J. and M. Core. 1997. Draft of DAMSL: Dialog Act Markup in Several Layers. www.cs.rochester.edu/research/cisd.Google Scholar
- Buckley, C. 1985. Implementation of the Smart information retrieval system. TR85-686, Computer Science, Cornell University. Google ScholarDigital Library
- Ferguson, G. and J. Allen. 1998. TRIPS: An Intelligent Integrated Problem-Solving Assistant. AAAI-98 Conf., pp. 567--573. Google ScholarDigital Library
- Fillmore, C. & C. F. Baker. 2001. Frame semantics for text understanding. WordNet Workshop at NAACL.Google Scholar
- Hardy, H., et al. 2002a. Cross-Document Summarization by Concept Classification. Proceedings of SIGIR, Tampere, Finland. Google ScholarDigital Library
- Hardy, H., et al. 2002b. Multi-layer Dialogue Annotation for Automated Multilingual Customer Service. ISLE Workshop, UK.Google Scholar
- Harabagiu, S., et. al. 2002. Answering Complex, List and Context questions with LCC's Question Answering Server. TREC-10.Google Scholar
- Hovy, E., et al. 2000. Question Answering in Webclopedia. Notebook. Proceedings of Text Retrieval Conference TREC-9.Google Scholar
- Humphreys, R. et al. 1998. Description of the LaSIE-II System as Used for MUC-7. Proc. of 7th Message Under. Conf. (MUC-7.).Google Scholar
- Levin, B. 1993. English Verb Class and Alternations: A Preliminary Investigation. Chicago: University of Chicago Press.Google Scholar
- Litman, Diane J. and Shimei Pan. 2002. Designing and Evaluating an Adaptive Spoken Dialogue System. User Modeling and User-Adapted Interaction. Vol. 12, No. 2/3, pp. 111--137. Google ScholarDigital Library
- Prager, J. et al, 2003. In Question-Answering Two Heads are Better Than One. Proceedings of HLT-NAACL 2003, pp 24--31. Google ScholarDigital Library
- Seneff, S. and J. Polifroni. 2000. Dialogue Management in the MERCURY Flight Reservation System. ANLP-NAACL 2000. Google ScholarDigital Library
- Small et al. 2004. A Data Driven Approach to Interactive Question Answering. In M. Maybury (ed). Future Directions in Automated Question Answering. MIT Press (to appear). Google ScholarDigital Library
- Strzalkowski, T and J. Wang. 1996. A self-learning Universal Concept Spotter. Proceedings of COLING-96, pp. 931--936. Google ScholarDigital Library
- Walker, M. A. 2002. An Application of Reinforcement Learning to Dialogue Strategy Selection in a Spoken Dialogue System for Email. Journal of AI Research, vol 12., pp. 387--416. Google ScholarDigital Library
- Wu, M. et al. 2003. Question Answering by Pattern Matching, Web-Proofing, Semantic Form Proofing. TREC-12.Notebook.Google Scholar
Recommendations
Hitiqa: High-quality intelligence through interactive question answering
We describe an interactive question answering system, HITIQA, which helps users find answers to complex analytical problems. Such problems often necessitate the user to submit not one but an entire series of questions, both simple and complex, and then ...
HITIQA: an interactive question answering system a preliminary report
MultiSumQA '03: Proceedings of the ACL 2003 workshop on Multilingual summarization and question answering - Volume 12HITIQA is an interactive question answering technology designed to allow intelligence analysts and other users of information systems to pose questions in natural language and obtain relevant answers, or the assistance they require in order to perform ...
HITIQA: a data driven approach to interactive analytical question answering
HLT-NAACL-Short '04: Proceedings of HLT-NAACL 2004: Short PapersIn this paper we describe the analytic question answering system HITIQA (High-Quality Interactive Question Answering) which has been developed over the last 2 years as an advanced research tool for information analysts. HITIQA is an interactive open-...
Comments