Question Answering over Unstructured Data without Domain Restrictions

Details Question Answering over Unstructured Data without Domain Restrictions Question Answering over Unstructured Data without Domain Restrictions

2002-07-14

arxiv.org/abs/cs/0207058v2

Computer Science

Computation and Language

8 pages, 6 figures, 5 tables. To appear in Proc. TaCoS'02, Potsdam, Germany

Scientific paper

Information needs are naturally represented as questions. Automatic Natural-Language Question Answering (NLQA) has only recently become a practical task on a larger scale and without domain constraints. This paper gives a brief introduction to the field, its history and the impact of systematic evaluation competitions. It is then demonstrated that an NLQA system for English can be built and evaluated in a very short time using off-the-shelf parsers and thesauri. The system is based on Robust Minimal Recursion Semantics (RMRS) and is portable with respect to the parser used as a frontend. It applies atomic term unification supported by question classification and WordNet lookup for semantic similarity matching of parsed question representation and free text.

Affiliated with

Also associated with

No associations

Rating

Question Answering over Unstructured Data without Domain Restrictions does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Question Answering over Unstructured Data without Domain Restrictions, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Question Answering over Unstructured Data without Domain Restrictions will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-375973