Abstract | ||
---|---|---|
This paper presents the architecture and functionality of a logic prover designed for question answering. The approach transforms questions and answer passages into logic representations based on syntactic, semantic and contextual information. World knowledge supplements the linguistic, ontological, and temporal axioms supplied to the prover which renders a deep understanding of the relationship between the question and answer text. The trace of the proofs provides a basis for generating human comprehensible answer justifications. The results show that the prover boosts the performance of the Question Answering system on TREC 2004 questions by 12%. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1016/j.jal.2005.12.005 | Journal of Applied Logic |
Keywords | Field | DocType |
Question answering,Natural language processing,Temporal reasoning,Automated reasoning,Ontologies | Ontology (information science),Automated reasoning,Ontology,Question answering,Information retrieval,Axiom,Computer science,Mathematical proof,Natural language processing,Artificial intelligence,Gas meter prover,Syntax | Journal |
Volume | Issue | ISSN |
5 | 1 | 1570-8683 |
Citations | PageRank | References |
26 | 1.16 | 8 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dan I. Moldovan | 1 | 2924 | 482.82 |
Christine Clark | 2 | 245 | 27.41 |
Sanda Harabagiu | 3 | 2203 | 221.65 |
Daniel Hodges | 4 | 45 | 4.32 |