Watson Discovery Advisor: Question-answering in an industrial setting

@inproceedings{Beller2016WatsonDA,
  title={Watson Discovery Advisor: Question-answering in an industrial setting},
  author={Charley Beller and G. Katz and A. Ginsberg and C. Phipps and Sean L. Bethard and Paul J Chase and Elinna Shek and K. Summers},
  year={2016}
}
  • Charley Beller, G. Katz, +5 authors K. Summers
  • Published 2016
  • Engineering
  • This work discusses a mix of challenges arising from Watson Discovery Advisor (WDA), an industrial strength descendant of the Watson Jeopardy! Question Answering system currently used in production in industry settings. Typical challenges include generation of appropriate training questions, adaptation to new industry domains, and iterative improvement of the system through manual error analyses. 
    1 Citations

    Tables from this paper

    References

    SHOWING 1-10 OF 25 REFERENCES
    Performance Issues and Error Analysis in an Open-Domain Question Answering System
    • 152
    • PDF
    A framework for merging and ranking of answers in DeepQA
    • 85
    • PDF
    Finding needles in the haystack: Search and candidate generation
    • 71
    • PDF
    A Survey of Answer Extraction Techniques in Factoid Question Answering
    • 45
    • PDF
    Building Watson: An Overview of the DeepQA Project
    • 1,283
    • PDF
    COGEX: A Logic Prover for Question Answering
    • 197
    • Highly Influential
    • PDF
    Special Questions and techniques
    • 19
    • PDF
    Fact-based question decomposition in DeepQA
    • 29
    • PDF
    Introduction to "This is Watson"
    • D. Ferrucci
    • Engineering, Computer Science
    • IBM J. Res. Dev.
    • 2012
    • 390
    Question analysis: How Watson reads a clue
    • 155
    • PDF