ABSTRACT
As the scale of available on-line data grows ever larger, individuals and businesses must cope with increasing complexity in decision-making processes which utilize large volumes of unstructured, semi-structured and/or structured data to satisfy multiple, interrelated information needs which contribute to an overall decision. Traditional decision support systems (DSSs) have been developed to address this need, but such systems are typically expensive to build, and are purpose-built for a particular decision-making scenario, making them difficult to extend or adapt to new decision scenarios. In this paper, we propose a novel decision representation which allows decision makers to formulate and organize natural language questions or assertions into an analytic hierarchy, which can be evaluated as part of an ad hoc decision process or as a documented, repeatable analytic process. We then introduce a new decision support framework, QUADS, which takes advantage of automatic question answering (QA) technologies to automatically understand and process a decision representation, producing a final decision by gathering and weighting answers to individual questions using a Bayesian learning and inference process. An open source framework implementation is presented and applied to two real world applications: target validation, a fundamental decision-making task for the pharmaceutical industry, and product recommendation from review texts, an everyday decision-making situation faced by on-line consumers. In both applications, we implemented and compared a number of decision synthesis algorithms, and present experimental results which demonstrate the performance of the QUADS approach versus other baseline approaches.
- A. Bauer-Mehren, M. Rautschka, F. Sanz, and L. I. Furlong. Disgenet: a cytoscape plugin to visualize, integrate, search and analyze gene--disease networks. Bioinformatics, 26(22):2924--2926, 2010. Google ScholarDigital Library
- F. Bex, J. Lawrence, M. Snaith, and C. Reed. Implementing the argument web. Commun. ACM, 56(10):66--73, Oct. 2013. Google ScholarDigital Library
- M. W. Bilotti and E. Nyberg. Evaluation for scenario question answering systems. In Proceedings of LREC '06 , pages 1536--1541, 2006.Google Scholar
- S. Chaudhuri, U. Dayal, and V. Narasayya. An overview of business intelligence technology. Commun. ACM, 54(8):88--98, Aug. 2011. Google ScholarDigital Library
- H. T. Dang, D. Kelly, and J. J. Lin. Overview of the trec 2007 question answering track. In Proceedings of TREC '07, 2007.Google Scholar
- W. Edwards, R. F. M. Jr., and e. Detlof von Winterfeldt. Advances in Decision Analysis. Cambridge University Press, 2007.Google ScholarCross Ref
- D. Ferrucci, E. Brown, J. Chu-Carroll, J. Fan, D. Gondek, A. A. Kalyanpur, A. Lally, J. W. Murdock, E. Nyberg, J. Prager, et al. Building watson: An overview of the deepqa project. AI magazine, 31(3):59--79, 2010.Google ScholarDigital Library
- W. Hersh and E. Voorhees. Trec genomics special issue overview. Inf. Retr. , 12(1):1--15, Feb. 2009. Google ScholarDigital Library
- R. A. Howard. Decision analysis: Applied decision theory. In Proceedings of ICORES '66, pages 304--328, 1966.Google Scholar
- R. A. Howard and J. E. Matheson. Influence diagrams. In Readings on the Principles and Applications of Decision Analysis , volume 2. Sdg Decision Systems, 1981. Google ScholarDigital Library
- J. Hughes, S. Rees, S. Kalindjian, and K. Philpott. Principles of early drug discovery. Br. J. Clin. Pharmacol., 162(6):1239--1249, 2011.Google ScholarCross Ref
- A. Kalyanpur, S. Patwardhan, B. Boguraev, A. Lally, and J. Chu-Carroll. Fact-based question decomposition for candidate answer re-ranking. In Proceedings of CIKM '11, pages 2045--2048, 2011. Google ScholarDigital Library
- B. Katz, G. Borchardt, and S. Felshin. Syntactic and semantic decomposition strategies for question answering from multiple sources. In Proceedings of AAAI '05 Workshop on Inference for Textual Question Answering, pages 35--41, 2005.Google Scholar
- U. B. Kjrulff and A. L. Madsen. Bayesian Networks and Influence Diagrams: A Guide to Construction and Analysis. Springer Publishing Company, Incorporated, 2nd edition, 2012. Google ScholarDigital Library
- J. Knowles and G. Gromo. Target selection in drug discovery. Nature Reviews Drug Discovery, 2(1):63--69, 2003.Google ScholarCross Ref
- F. Lacatusu, A. Hickl, and A. Harabagiu. Impact of question decomposition on the quality of answer summaries. In Proceedings of LREC '06, pages 1147--1153, 2006.Google Scholar
- S. L. Lauritzen and D. Nilsson. Representing and solving decision problems with limited information. Manage. Sci., 47(9):1235--1251, Sept. 2001. Google ScholarDigital Library
- Q. Liu and A. T. Ihler. Belief propagation for structured decision making. In UAI '12, pages 523--532, 2012.Google Scholar
- J. D. Lowrance, I. W. Harrison, and A. C. Rodriguez. Capturing analytic thought. In Proceedings of K-CAP '01, pages 84--91, 2001. Google ScholarDigital Library
- J. L. Malin. Envisioning watson as a rapid-learning system for oncology. Journal of Oncology Practice, 9(3):155--157, 2013.Google ScholarCross Ref
- D. D. Mauá, C. P. de Campos, and M. Zaffalon. Solving limited memory influence diagrams. J. Artif. Int. Res., 44(1):97--140, May 2012. Google ScholarDigital Library
- J. McAuley and J. Leskovec. Hidden factors and hidden topics: Understanding rating dimensions with review text. In Proceedings of RecSys '13, pages 165--172, 2013. Google ScholarDigital Library
- J. R. Miller. Professional Decision-Making: a procedure for evaluating complex alternatives. Praeger Publishers, 1970.Google Scholar
- J. W. Murdock, J. Fan, A. Lally, H. Shima, and B. Boguraev. Textual evidence gathering and analysis. IBM Journal of Research and Development, 56(3.4):8:1--8:14, 2012. Google ScholarDigital Library
- K. P. Murphy, Y. Weiss, and M. I. Jordan. Loopy belief propagation for approximate inference: An empirical study. In Proceedings of UAI '99, pages 467--475, 1999. Google ScholarDigital Library
- A. Nath and P. Domingos. Efficient belief propagation for utility maximization and repeated inference. In Proceedings of AAAI '10, pages 1187--1192, 2010.Google Scholar
- A. Peñas, E. Hovy, P. Forner, A. Rodrigo, R. Sutcliffe, and R. Morante. Qa4mre 2011--2013: Overview of question answering for machine reading evaluation. In Information Access Evaluation. Multilinguality, Multimodality, and Visualization, volume 8138, pages 303--320. Springer Berlin Heidelberg, 2013.Google Scholar
- A. Pollock and A. Hockley. What's wrong with internet searching. In Designing for the Web: Empirical Studies, 1996.Google Scholar
- J. Prager, J. Chu-Carroll, and K. Czuba. Question answering using constraint satisfaction: Qa-by-dossier-with-constraints. In Proceedings of ACL '04, 2004. Google ScholarDigital Library
- J. F. Pritchard, M. Jurima-Romet, M. L. Reimer, E. Mortimer, B. Rolfe, and M. N. Cayen. Making better drugs: Decision gates in non-clinical drug development. Nature Reviews Drug Discovery, 2(7):542--553, 2003.Google ScholarCross Ref
- T. L. Saaty. What is the analytic hierarchy process? Springer, 1988.Google ScholarCross Ref
- E. Saquete, P. Martínez-Barco, R. Muñoz, and J. L. Vicedo. Splitting complex temporal questions for question answering systems. In Proceedings of ACL '04, 2004. Google ScholarDigital Library
- J. Sprague, Ralph H. A framework for the development of decision support systems. MIS Quarterly, 4(4):pp. 1--26, 1980. Google ScholarDigital Library
- D. von Winterfeldt. Bridging the gap between science and decision making. Proceedings of the National Academy of Sciences, 110(Supplement 3):14055--14061, 2013.Google ScholarCross Ref
- D.-L. Xu, McCarthy, and J.-B. Yang. Intelligent decision system and its application in business innovation self assessment. Decision Support Systems, 42(2):664--673, 2006. Google ScholarDigital Library
- F. Yang, J. Feng, and G. Di Fabbrizio. A data driven approach to relevancy recognition for contextual question answering. In Proceedings of HLT-NAACL '06 Workshop on Interactive Question Answering Workshop (IQA), pages 33--40, 2006. Google ScholarDigital Library
- Z. Yang, E. Garduno, Y. Fang, A. Maiberg, C. McCormack, and E. Nyberg. Building optimal information systems automatically: Configuration space exploration for biomedical information systems. In Proceedings of CIKM '13, 2013. Google ScholarDigital Library
Index Terms
- QUADS: question answering for decision support
Recommendations
A framework for design of an integrated system for decision support and training
ECCE '13: Proceedings of the 31st European Conference on Cognitive ErgonomicsThis paper introduces a cognitive engineering approach for requirements definition and design of an integrated system for decision support and training for critical situations. Effective decision support and training should be provided not only for ...
Providing Decisional Guidance for Multicriteria Decision Making in Groups
Intelligent user interfaces, particularly in interactive group settings, can be based on system explanations that guide model building, application, and interpretation. Here we extend Silver's (1990, 1991) conceptualization of decisional guidance and ...
Decisions for information or information for decisions? Optimizing information gathering in decision-intensive processes
AbstractDecision-intensive business processes are performed by decision makers who gather different pieces of information to reach the process objective: a final decision of high quality, for instance, the final price of a quote or the ...
Highlights- Information-gathering for decision-making in business processes is optimized.
- ...
Comments