Hostname: page-component-586b7cd67f-t7fkt Total loading time: 0 Render date: 2024-11-22T00:05:53.176Z Has data issue: false hasContentIssue false
  • English
  • Français

Parallel and nested decomposition for factoid questions

Published online by Cambridge University Press:  29 October 2013

BRANIMIR BOGURAEV ,
SIDDHARTH PATWARDHAN ,
ADITYA KALYANPUR ,
JENNIFER CHU-CARROLL  and
ADAM LALLY
BRANIMIR BOGURAEV
Affiliation:
IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY 10598. USA e-mail: bran@us.ibm.com, siddharth@us.ibm.com, adityakal@us.ibm.com, jencc@us.ibm.com, alally@us.ibm.com
SIDDHARTH PATWARDHAN
Affiliation:
IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY 10598. USA e-mail: bran@us.ibm.com, siddharth@us.ibm.com, adityakal@us.ibm.com, jencc@us.ibm.com, alally@us.ibm.com
ADITYA KALYANPUR
Affiliation:
IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY 10598. USA e-mail: bran@us.ibm.com, siddharth@us.ibm.com, adityakal@us.ibm.com, jencc@us.ibm.com, alally@us.ibm.com
JENNIFER CHU-CARROLL
Affiliation:
IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY 10598. USA e-mail: bran@us.ibm.com, siddharth@us.ibm.com, adityakal@us.ibm.com, jencc@us.ibm.com, alally@us.ibm.com
ADAM LALLY
Affiliation:
IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY 10598. USA e-mail: bran@us.ibm.com, siddharth@us.ibm.com, adityakal@us.ibm.com, jencc@us.ibm.com, alally@us.ibm.com
Get access Rights & Permissions [Opens in a new window]

Abstract

Typically, automatic Question Answering (QA) approaches use the question in its entirety in the search for potential answers. We argue that decomposing complex factoid questions into separate facts about their answers is beneficial to QA, since an answer candidate with support coming from multiple independent facts is more likely to be the correct one. We broadly categorize decomposable questions as parallel or nested, and we present a novel question decomposition framework for enhancing the ability of single-shot QA systems to answer complex factoid questions. Essential to the framework are components for decomposition recognition, question rewriting, and candidate answer synthesis and re-ranking. We discuss the interplay among these, with particular emphasis on decomposition recognition, a process which, we argue, can be sufficiently informed by lexico-syntactic features alone. We validate our approach to decomposition by implementing the framework on top of IBM Watson™, a state-of-the-art QA system, and showing a statistically significant improvement over its accuracy.

Type
Articles
Information
Natural Language Engineering , Volume 20 , Issue 4 , October 2014 , pp. 441 - 468
Copyright
Copyright © Cambridge University Press 2013 

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

Chu-Carroll, J., Brown, E., Lally, A., and Murdock, J. W. 2012a. Identifying implicit relationships. IBM Journal of Research and Development 56 (3.4): 12:1–10.Google Scholar
Chu-Carroll, J., Fan, J., Boguraev, B., Carmel, D., Sheinwald, D., and Welty, C. 2012b. Finding needles in the haystack: search and candidate generation. IBM Journal of Research and Development 56 (3.4): 6:1–12.CrossRefGoogle Scholar
Chu-Carroll, J., Fan, J., Schlaefer, N., and Zadrozny, W. 2012c. Textual resource acquisition and engineering. IBM Journal of Research and Development 56 (3.4): 4:1–11.CrossRefGoogle Scholar
Ferrucci, D., Brown, E., Chu-Carroll, J., Fan, J., Gondek, D., Kalyanpur, A., Lally, A., Murdock, J. W., Nyberg, E., Prager, J., Schlaefer, N., and Welty, C., 2010. Building Watson: an overview of the DeepQA project. AI Magazine 31 (3): 59–79.Google Scholar
Gondek, D. C., Lally, A., Kalyanpur, A., Murdock, J. W., Duboue, P. A., Zhang, L., Pan, Y., Qiu, Z. M., and Welty, C. 2012. A framework for merging and ranking of answers in DeepQA. IBM Journal of Research and Development 56 (3.4): 14:1–12.CrossRefGoogle Scholar
Hartrumpf, S. 2008. Semantic decomposition for question answering. In Proceedings of the 18th European Conference on Artificial Intelligence, pp. 313–7. Amsterdam, Netherlands: IOS Press.Google Scholar
Kalyanpur, A., Boguraev, B., Patwardhan, S., Murdock, J. W., Lally, A., Welty, C., Prager, J., Coppola, B., Fokoue-Nkoutche, A., Zhang, L., Pan, Y., and Qiu, Z. M. 2012a. Structured data and inference in DeepQA. IBM Journal of Research and Development 56 (3.4): 10:1–14.Google Scholar
Kalyanpur, A., Patwardhan, S., Boguraev, B., Lally, A., and Chu-Carroll, J. 2011. Fact-based question decomposition for candidate answer re-ranking. In Proceedings of the 20th ACM International Conference on Information and Knowledge Management (CIKM '11), pp. 2045–8. Glasgow, UK: ACM Digital Library.Google Scholar
Kalyanpur, A., Patwardhan, S., Boguraev, B., Lally, A., and Chu-Carroll, J. 2012b. Fact-based question decomposition in DeepQA. IBM Journal of Research and Development 56 (3.4): 13:1–11.Google Scholar
Katz, B., Borchardt, G., and Felshin, S. 2005. Syntactic and semantic decomposition strategies for question answering from multiple sources. In Proceedings of the AAAI Workshop on Inference for Textual Question Answering, pp. 35–41. Menlo Park, CA: AAAI Press.Google Scholar
Katz, B., Lin, J., and Quan, D. 2002. Natural language annotations for the semantic web. In Proceedings of International Conference on Ontologies, Databases and Applications of Semantics, pp. 1317–31. Berlin, Germany: Springer-Verlag.Google Scholar
Lacatusu, F., Hickl, A., and Harabagiu, S. 2006. The impact of question decomposition on the quality of answer summaries. In Proceedings of the Fifth Language Resources and Evaluation Conference, pp. 1147–52. Genoa, Italy: European Language Resources Association (ELRA).Google Scholar
Lally, A., Prager, J., McCord, M. C., Boguraev, B., Patwardhan, S., Fan, J., Fodor, P., and Chu-Carroll, J. 2012. Question analysis: how Watson reads a clue. IBM Journal of Research and Development 56 (3.4): 2:1–14.Google Scholar
Lin, C., and Liu, R. 2008. An analysis of multi-focus questions. In Proceedings of the SIGIR 2008 Workshop on Focused Retrieval, pp. 30–6. Singapore: ACM.Google Scholar
McCord, M. 1989. Slot grammar: a system for simpler construction of practical natural language grammars. In Proceedings of the International Symposium on Natural Language and Logic, pp. 118–145. Hamburg, Germany: Springer-Verlag.Google Scholar
McCord, M. C., Murdock, J. W., and Boguraev, B. 2012. Deep parsing in Watson. IBM Journal of Research and Development 56 (3.4): 3:1–15.Google Scholar
McNemar, Q., 1947. Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika 12 (2): 153–7.CrossRefGoogle ScholarPubMed
Murdock, J. W., Fan, J., Lally, A., Shima, H., and Boguraev, B. 2012a. Textual evidence gathering and analysis. IBM Journal of Research and Development 56 (3.4): 8:1–14.Google Scholar
Murdock, J. W., Kalyanpur, A., Welty, C., Fan, J., Ferrucci, D., Gondek, D. C., Zhang, L., and Kanayama, H. 2012b. Typing candidate answers using type coercion. IBM Journal of Research and Development 56 (3.4): 7:1–13.Google Scholar
Prager, J., Brown, E., and Chu-Carroll, J. 2012. Special questions and techniques. IBM Journal of Research and Development 56 (3.4): 11:1–13.Google Scholar
Prager, J., Chu-Carroll, J., and Czuba, K. 2004. Question answering by constraint satisfaction: QA-by-dossier with constraints. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, pp. 574–81. Barcelona, Spain: ACL.Google Scholar
Saquete, E., Martínez-Barco, P., Muñoz, R., and Vicedo, J. 2004. Splitting complex temporal questions for question answering systems. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, pp. 566–73. Barcelona, Spain: ACL.Google Scholar
Soricut, R., and Brill, E. 2004. Automatic question answering: beyond the factoid. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pp. 57–64. Boston, MA: ACL.Google Scholar
Voorhees, E. 2002. Overview of the TREC 2002 question answering track. In NIST Special Publication 500-251: The Eleventh Text Retrieval Conference (TREC 2002), pp. 115–123. Gaithersburg, MD: Department of Commerce, National Institute of Standards and Technology.Google Scholar
Wang, C., Kalyanpur, A., Fan, J., Boguraev, B. K., and Gondek, D. C. 2012. Relation extraction and scoring in DeepQA. IBM Journal of Research and Development 56 (3.4): 9:1–12.Google Scholar
Witten, I., and Frank, E., 2000. Data Mining – Practical Machine Learning Tools and Techniques with Java Implementations. San Francisco, CA: Morgan-Kaufmann.Google Scholar