ABSTRACT
Existing search engines generally retrieve information in response to logical queries consisting of keywords. In contrast, the agent system presented in this paper, DOrAM Domain Oriented Answering Machine), enables a user to submit a natural language question to the Web, and exploits the question's semantics (along with its keywords) in its search. Moreover, DOrAM improves upon the performance of existing search engines by returning content-based answers to the user's query.The DOrAM query-response agent is composed of four modules, corresponding to its four-stage approach to question answering. First, the domain of interest is defined in terms of characteristic concepts given by a human expert. Second, documents are gathered from the World Wide Web that are all related to this specialized domain. Third, an ontology is automatically constructed for this domain; this ontology encodes subject-action-object relations found in Web documents gathered in the previous step. The fourth step is the actual question answering stage, returning knowledge that was assembled in light of the user's question and the domain ontology.
- C. Goldman, A. Langer, and J. Rosenschein. Musag - an agent that learns what you mean. Journal of Applied AI 11(5):413--435, 1997. Edited by N. Jennings and B. CrabtreeGoogle Scholar
- G. Miller, R. Beckwith, C. Fellbaum, D. Gross, and K. Miller. Introduction to WordNet: An on-line lexical database. International Journal of Lexicography, 3(4):235--244, 1991Google ScholarCross Ref
- D. Moldovan, S. Harabagiu, M. Pasca, R. Mihalcea, R. Goodrum, R. Girju, and V. Rus. Lasso: A tool for surfing the answer net. In Procs. of TREC-8, Oct 1999Google Scholar
- R. Srihari and W. Li. Information extraction supported question answering. In Procs. of TREC-8, Oct 1999Google Scholar
Index Terms
- DOrAM: real answers to real questions
Recommendations
Re-ranking search results using query logs
CIKM '06: Proceedings of the 15th ACM international conference on Information and knowledge managementThis work addresses two common problems in search, frequently occurring with underspecified user queries: the top-ranked results for such queries may not contain documents relevant to the user's search intent, and fresh and relevant pages may not get ...
A study of results overlap and uniqueness among major web search engines
The performance and capabilities of Web search engines is an important and significant area of research. Millions of people world wide use Web search engines very day. This paper reports the results of a major study examining the overlap among results ...
Site-searching strategies of searchers referred from search engines
ASIST '13: Proceedings of the 76th ASIS&T Annual Meeting: Beyond the Cloud: Rethinking Information BoundariesIn this research, we analyze the referral queries and associated site-search queries at the session level from searchers coming from web search engines. Findings are based on a random sample of 10,000 from a total of 327,261 searching sessions of an ...
Comments