ABSTRACT
We describe ongoing research using natural English text queries as an intelligent interface for inferring answers from structured data in a specific domain. Users can express queries whose answers need to be deduced from data in different databases, without knowing the structures of those databases nor even the existence of the sources used. Users can pose queries incrementally, elaborating on an initial query, and ask follow-up questions based on answers to earlier queries.
Inference in an axiomatic theory of the subject domain links the natural form in which the question is posed to the way relevant data is represented in a database, and composes information obtained from several databases into an answer to a complex question.
We describe the status of a prototype system, called Quadri, for answering questions about HIV treatment, using the Stanford HIV Drug Resistance Database [8] and European resources. We discuss some of the problems that need to be solved to make this approach work, and some of our solutions.
- Bobrow, D. G. et al. PARC's Bridge and Question Answering System. Proceedings of the Grammar Engineering Across Frameworks (GEAF07) Workshop, pp. 46--66, CSLI Publications, 2007.Google Scholar
- Bobrow. D.G. et al. A Basic Logic for Textual Inference. AAAI Workshop on Inference for Textual Question Answering, Pittsburgh, PA, 2005.Google Scholar
- Crouch, D. and King, T. H. Semantics via F-Structure Rewriting. Proceedings of LFG06, CSLI On-line publications, 2006.Google Scholar
- Elfsoft www.elfsoft.co.Google Scholar
- Katz, B. et al. The Start Multimedia Information System: Current Technology and Future Directions. Multimedia Information Systems, 2002.Google Scholar
- Maxwell, J. T. and Kaplan, R. M. An Efficient Parser for LFG. Butt, M. and King, T. H. (editors).Google Scholar
- On-line Proceedings of the LF G96 Conference. http://csli-publications.stanford.edu/publications. 1996.Google Scholar
- Popescu, A. M., Etzioni, O. and Kautz, H. Towards a Theory of Natural Language Interfaces to Databases. Proceedings of IUI 200. Google ScholarDigital Library
- Rhee, S. Y. et al. Human Immunodeficiency Virus Reverse Transcriptase and Protease Sequence Database. Nucleic Acids Res 31:298--303, 2003.Google ScholarCross Ref
- Stickel, M. et al. A Guide to SNARK. www.ai.sri.com/snark/tutorial.htm.Google Scholar
- Stickel, M. et al. Deductive Composition of Astronomical Software from Subroutine Libraries. Automated Deduction 12, Nancy, France, June 1994. Google ScholarDigital Library
- Waldinger, R. et al. Deductive Question Answering from Multiple Resources. New Directions in Question Answering, AAAI, 2004.Google Scholar
- Woods, W. A. et al. The Lunar Sciences Natural Language Information System: BBN Report No. 2378, Bolt Beranek and Newman Inc., Cambridge, MA 02138. (NTIS -- available as N72--28984.), June, 1972.Google Scholar
Index Terms
- Deducing answers to english questions from structured data
Recommendations
English Access to Structured Data
ICSC '11: Proceedings of the 2011 IEEE Fifth International Conference on Semantic ComputingWe present work on using a domain model to guide text interpretation, in the context of a project that aims to interpret English questions as a sequence of queries to be answered from structured databases. We adapt a broad-coverage and ambiguity-enabled ...
Best answers over incomplete data: complexity and first-order rewritings
IJCAI'19: Proceedings of the 28th International Joint Conference on Artificial IntelligenceAnswering queries over incomplete data is ubiquitous in data management and in many AI applications that use query rewriting to take advantage of relational database technology. In these scenarios one lacks full information on the data but queries still ...
Answering Count Questions with Structured Answers from Text
AbstractIn this work we address the challenging case of answering count queries in web search, such as number of songs by John Lennon. Prior methods merely answer these with a single, and sometimes puzzling number or return a ranked list of ...
Comments