Tianwang at TREC-2006 QA track

From WikiPapers
Revision as of 06:32, November 8, 2014 by Nemo bis (Talk | contribs) (CSV import from another resource for wiki stuff; all data is PD-ineligible, abstracts quoted under quotation right. Skipping when title already exists. Sorry for authors and references to be postprocessed, please edit and create redirects.)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Tianwang at TREC-2006 QA track is a 2006 conference paper written in English by He J., Liu Y. and published in NIST Special Publication.

[edit] Abstract

This paper describes the architecture and implementation of Tianwang QA system2006, which works for the TREC QA Main task this year. The main improvement is: 1. add one well founded knowledge source from Web - Wikipedia, and employ some natural language processing technologies to extract high quality answers; 2. design and implement a new translation algorithm in query generation. The results show that fine organized knowledge source is effective in answering all three types of questions. And such query generation algorithm can be benefit from both Frequent Asked Questions on Web and past TREC QA data.

[edit] References

This section requires expansion. Please, help!

Cited by

Probably, this publication is cited by others, but there are no articles available for them in WikiPapers.