Abstract | ||
---|---|---|
This report describes the Xerox work on the TREC-8 Question Answering Track. We linkedtogether a few basic NLP components (a question parser, a sentence boundary identifier, and aproper noun tagger) with a sentence scoring function and an answer presentation function builtspecifically for the TREC Q&A task. Our system found the correct 50-byte answer (in the top 5responses) to 45% of the questions, a quite respectable performance, but with considerable roomfor improvement. Based on... |
Year | Venue | Keywords |
---|---|---|
1999 | TREC | question answering,score function,noun |
Field | DocType | Citations |
Data mining,Question answering,Information retrieval,Computer science | Conference | 44 |
PageRank | References | Authors |
2.47 | 0 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
David A. Hull | 1 | 1282 | 214.27 |