ABSTRACT
We present a new technique for question answering called Predictive Annotation. Predictive Annotation identifies potential answers to questions in text, annotates them accordingly and indexes them. This technique, along with a complementary analysis of questions, passage-level ranking and answer selection, produces a system effective at answering natural-language fact-seeking questions posed against large document collections. Experimental results show the effects of different parameter settings and lead to a number of general observations about the question-answering problem.
- 1.AAAI Fall Symposium on Question Answering, North Falmouth, MA, 1999.Google Scholar
- 2.R. Byrd and Y. Ravin. "Identifying and Extracting Relations in Text", Proceedings of NLDB 99, Klagenfurt, Austria.Google Scholar
- 3.V. Chaudhri and R. Fikes. Question answering systems: Papers from the 1999 AAAI fall symposium. Technical Report FS-99-02, AAAI Press, 1999.Google Scholar
- 4.F.J. Damerau. Problems and some solutions in customization of natural language database front ends. ACM Trans. Inf. Syst., 3(2):165-184, Apr. 1985. Google ScholarDigital Library
- 5.D. Harman and E. Voorhees, editors. The Eighth Text REtrieval Conference (TREC-8), Gaithersburg, MD, 2000. National Institute of Standards and Technology Special Publication.Google Scholar
- 6.D. Hawking, N. Craswell, and P. Thistlewaite. Overview of TREC-7 very large collection track. In D. K. Harman and E. M. Voorhees, editors, The Seventh Text REtrieval Conference (TREC-7), pages 91-104, Gaithersburg, MD, 1999. National Institute of Standards and Technology Special Publication 500-242.Google Scholar
- 7.V. A. Kulyukin, K.J. Hammond, and R.D. Burke. "Answering Questions for an Organization Online", Proceedings of AAAI'98. Google ScholarDigital Library
- 8.J. Kupiec. "Murax: A Robust Linguistic Approach for Question Answering Using an On-line Encyclopaedia", Proceedings of SIGIR'93. Google ScholarDigital Library
- 9.G. Miller. "WordNet: A Lexical Database for English", Communications of the ACM 38(11) pp 39- 41, 1995 Google ScholarDigital Library
- 10.Proc. of the Sixth Message Understanding Conference (MUC-6), November 1995, San Francisco: Morgan Kaufmann.Google Scholar
- 11.E. Rosch et al. "Basic Objects in Natural Categories", Cognitive Psychology 8, 382-439, 1976.Google ScholarCross Ref
- 12.G. Salton and M.J. McGill. Introduction to Modern Information Retrieval. McGraw-Hill, New York, 1983. Google ScholarDigital Library
- 13.R. Sfihari and W. Li. "Question Answering Supported by Information Extraction", Proceedings of TREC8, Gaithersburg, Md., 1999.Google Scholar
- 14.TREC Q&A Evaluation official Web site: http://www.research.att.com/~singhal/qatrack.htrnlGoogle Scholar
- 15.E. Turban and J. Aronson. Decision Support Systems and Intelligent Systems. Prentice Hall, 1998. Google ScholarDigital Library
- 16.E. Voorhees. "Query Expansion using Lexical- Semantic Relations", Proceedings ofSIGIR'94, 61- 69. 1994. Google ScholarDigital Library
- 17.N. Wacholder, Y. Ravin and M. Choi. "Disarnbiguation of Proper Names in Text", Proceedings ofANLP'97. Washington, DC, April 1997. Google ScholarDigital Library
- 18.I.H. Witten, A. Moffat, and T.C. Bell. Managing Gigabytes: Compressing and Indexing Documents and Images. Van Nostrand Reinhold, New York, 1994. Google ScholarDigital Library
- 19.E.W. Brown and H.A. Chong. The Guru System in TREC-6. Proceedings of TREC6, Gaithersburg, MD, 1998.Google Scholar
- 20.J.M. Prager, D. Radev, E.W. Brown and A.R. Coden. "The Use of Predictive Annotation for Question-Answering in TREC8", Proceedings of TREC8, Gaithersburg, MD., 2000.Google Scholar
- 21.D. Radev, J.M., Prager and V. Saran. "Ranking Suspected Answers to Natural Language Questions using Predictive Annotation", to be published in Proceedings of ANLP'O0, Seattle, WA, 2000. Google ScholarDigital Library
Index Terms
- Question-answering by predictive annotation
Recommendations
Quality-aware collaborative question answering: methods and evaluation
WSDM '09: Proceedings of the Second ACM International Conference on Web Search and Data MiningCommunity Question Answering (QA) portals contain questions and answers contributed by hundreds of millions of users. These databases of questions and answers are of great value if they can be used directly to answer questions from any user. In this ...
Will my question be answered? predicting "Question Answerability" in community question-answering sites
ECMLPKDD'13: Proceedings of the 2013th European Conference on Machine Learning and Knowledge Discovery in Databases - Volume Part IIIAll askers who post questions in Community-based Question Answering (CQA) sites such as Yahoo! Answers, Quora or Baidu's Zhidao, expect to receive an answer, and are frustrated when their questions remain unanswered. We propose to provide a type of "...
A community question-answering refinement system
HT '11: Proceedings of the 22nd ACM conference on Hypertext and hypermediaCommunity Question Answering (CQA) websites, which archive millions of questions and answers created by CQA users to provide a rich resource of information that is missing at web search engines and QA websites, have become increasingly popular. Web ...
Comments