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. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1145/544862.544926 | AAMAS |
Keywords | Field | DocType |
doram query-response agent,domain ontology,real answer,web document,existing search engine,natural language question,ontology encode,actual question answering stage,doram domain,specialized domain,real question,world wide web,information retrieval,information integration,question answering,search engine,natural language | Ontology,Information integration,Question answering,Search engine,Information retrieval,Computer science,Exploit,Natural language,Answering Machine,Semantics | Conference |
ISBN | Citations | PageRank |
1-58113-480-0 | 0 | 0.34 |
References | Authors | |
3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taras Mahlin | 1 | 0 | 0.34 |
Jeffrey S. Rosenschein | 2 | 2781 | 527.83 |
Claudia V. Goldman | 3 | 726 | 64.56 |