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 Christopher Phipps and Sean L. Bethard and Paul J. Chase and Elinna Shek and K. Summers},
  year={2016}
}
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
A framework for merging and ranking of answers in DeepQA
Finding needles in the haystack: Search and candidate generation
A Survey of Answer Extraction Techniques in Factoid Question Answering
Building Watson: An Overview of the DeepQA Project
COGEX: A Logic Prover for Question Answering
Special Questions and techniques
Fact-based question decomposition in DeepQA
Introduction to "This is Watson"
  • D. Ferrucci
  • Engineering, Computer Science
  • IBM J. Res. Dev.
  • 2012
Question analysis: How Watson reads a clue
UIMA: an architectural approach to unstructured information processing in the corporate research environment
...
1
2
3
...