Hostname: page-component-7c8c6479df-24hb2 Total loading time: 0 Render date: 2024-03-29T07:39:42.249Z Has data issue: false hasContentIssue false

HITIQA: High-quality intelligence through interactive question answering

Published online by Cambridge University Press:  01 January 2009

S. SMALL
Affiliation:
Language Analytic Corporation, Schenectady, NY, USA e-mail: small@laancor.com
T. STRZALKOWSKI
Affiliation:
Institute of Informatics, Logics and Security Studies, University at Albany, State University of New York, Albany, NY, USA e-mail: tomek@csc.albany.edu

Abstract

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 to negotiate the final content and form of the answer. HITIQA advances research in human–computer dialogue by enabling topical, mixed initiative interaction over unstructured data. HITIQA uses the process of text framing to bring a level of semantic representation to open-domain data in order to facilitate meaningful dialogue with the user. In this paper we give an overview of HITIQA's design and explain the workings of its main components with particular attention given to its dialogue capabilities. We also present results of end-to-end system evaluations that demonstrate the effectiveness of the system as a whole, as well as contributions of the individual components and specifically the benefits of our dialogue-based approach. While our research continues, a number of HITIQA prototypes have recently been deployed at various government agencies where they are being tested under real operational conditions.

Type
Papers
Copyright
Copyright © Cambridge University Press 2008

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Allen, J., Schubert, L., Ferguson, G., Heeman, P., Hwang, C., Kato, T., Light, M., Martin, N., Miller, B., Posesio, M., and Traum, D. 1995. The TRAINS project: a case study in building a conversational planning agent. Journal of Experimental and Theoretical Artificial Intelligence 7: 748.CrossRefGoogle Scholar
Bertomeau, N., Uszkoreit, H., Frank, A., Krieger, H., and Jorg, B. 2006. Contextual phenonmena and thematic relations in database qa dialogues: results from a wizard-of-oz experiment. In Worshop on Interactive Question Answering, HLT-NAACL 2006, New York.Google Scholar
Callan, J., Croft, W., and Harding, S. 1992. The inquery retrieval system. In Proceedings of the 3rd International Conference on Database and Expert Systems, Valencia, Spain.Google Scholar
Clough, P., Gaizauskas, R., Piao, S., and Wilks, Y. 2002. Meter: measuring text reuse. In Proceedings of the 40th Anniversary Meeting for the Association for Computational Linguistics (ACL-02), University of Pennsylvania, Philadelphia, USA, pp. 152–59.Google Scholar
De Roeck, A., Kruschwitz, U., Scott, P., Steel, S., Turner, R., and Webb, N. 2000. The YPA – An assistant for classified directory enquiry. In Intelligent Systems and Soft Computing: Prospects, Tools and Applications. Lecture Notes in Artificial Intelligence (LNAI), vol. 1804. Springer Verlag.Google Scholar
Glass, J., Flammia, G., Goodine, D., Phillips, M., Polifroni, J., Sakai, S., Seneff, S., and Zue, V. 1995. Multilingual spoken-language understanding in the MIT VOYAGER System. Speech Communication 17: 118.CrossRefGoogle Scholar
Harabagiu, S., Hickl, A., Lehmann, J., and Moldovan, D. 2005. Experiments with interactive question-answering. In Proceedings of the 43rd AnnualMeeting of the ACL, Ann Arbor, MI, pp. 205–14.Google Scholar
Harabagiu, S., Moldovan, D., Pasca, M., Surdeanu, M., Mihalcea, R., Girju, R., Rus, V., Lacatusu, F., Morarescu, P., and Bunescu, R. 2002. Answering complex, list and context questions with lccs question answering server. In Proceedings of Text Retrieval Conference (TREC-10), Gaithersburg, MD.Google Scholar
Hardy, H., Kanchakouskaya, V., and Strzalkowski, T. 2006. Automatic event classification using surface text features. In Proceedings of the AAAI Workshop on Event Extraction and Synthesis, Boston, MA.Google Scholar
Hardy, H., Shimizu, N., Strzalkowski, T., Wise, B., and Zhang, X. 2002. Cross-document summarization by concept classification. In Proceedings of SIGIR-2002, Tampere.CrossRefGoogle Scholar
Hardy, H., Strzalkowski, T., and Wu, M. 2003. Dialogue management for an automated multilingual call center. In Proceedings of the HLT-NAACL 2003 Workshop: Research Directions in Dialogue Processing, Edmonton, Alberta, Canada, pp. 1012.CrossRefGoogle Scholar
Hovy, E., Gerber, L., Hermjakob, U., Junk, M., and Lin, C. 2000. Question answering in webclopedia. In Proceedings of Text Retrieval Conference (TREC-9), Gaithersburg, MD.Google Scholar
Kelly, D., Kantor, P., Morse, E., Scholtz, J., and Sun, Y. 2006. User-centered evaluation of interactive question answering systems. In Worshop on Interactive Question Answering, HLT-NAACL 2006, New York.Google Scholar
Koenemman, J., and Belkin, N. 1996. A case for interaction: a study of interactive information retrieval behavior and effectiveness. In CHI'96 Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems, New York: ACM, pp. 205–12.Google Scholar
Miller, D., Schwartz, R., Weischedel, R., and Stone, R. 1999. Named entity extraction from broadcast news. In Proceedings of DARPA Broadcast News Workshop, Herndon, VA.Google Scholar
Morse, E., and Sholtz, J. 2004. An investigation of evaluation metrics for analytic question answering. In Proceedings of AQUAINT Phase 2 6-month PI Meeting, Tampa.Google Scholar
Prager, J., Chu-Carroll, J., Czuba, K., and Ittyercheriah, A. 2003. In question-answering two heads are better than one. In Proceedings of HLT-NAACL 2003, Edmonton, AB, Canada, pp. 2431.Google Scholar
Searle, J. R. 1969. Speech Acts: An Essay in the Philosophy of Language. Cambridge: Cambridge University Press.CrossRefGoogle Scholar
Small, S., Shimizu, N., Strzalkowski, T., and Liu, T. 2003. Hitiqa: a data driven approach to interactive question answering, a preliminary report. In Proceedings of AAAI New Directions in Question Answering Spring Symposium 2003, San Jose, California, pp. 94104.Google Scholar
Small, S., Strzalkowski, T., Liu, T., Shimizu, N., and Yamrom, B. 2004. A data driven approach to interactive QA. In Maybury, M. (ed.), New Directions in Question Answering, pp. 129–40. MIT press.Google Scholar
Strzalkowski, T., and Wang, J. 1996. A self-learning universal concept spotter. In Proceedings of the 16th conference on Computational Lingusitics, Association for Computational Linguistics, Copenhagen, Denmark, vol. 2, pp. 931–36.Google Scholar
Ward, W., and Pellom, B. 1999. The CU Communicator system. In Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, Keystone, CO, pp. 341–44.Google Scholar
Yangarber, R., Grishman, R., Tapanainen, P., and Huttunen, S. 2000. Unsupervised discover of scenario-level patterns for information extraction. In Proceedings of the 6th conference on Applied Natural Language Processing, Seattle, WA.Google Scholar