Abstract | ||
---|---|---|
This report describes the system developed by the University of Edinburgh and the Univer- sity of Sydney for the TREC-2005 question answering evaluation exercise. The backbone of our question-answering platform is QED, a linguistically-principled QA system. We ex- perimented with external sources of knowl- edge, such as Google and Wikipedia, to en- hance the performance of QED, especially for reranking and off-line processing of the corpus. For factoid and list questions we performed sig- nificantly above the median accuracy score of all participating systems at TREC 2005. |
Year | Venue | Keywords |
---|---|---|
2005 | TREC | question answering |
Field | DocType | Citations |
Data mining,Question answering,Information retrieval,Computer science,Factoid | Conference | 19 |
PageRank | References | Authors |
1.37 | 6 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kisuh Ahn | 1 | 35 | 4.53 |
Johan Bos | 2 | 954 | 89.07 |
David Kor | 3 | 19 | 1.37 |
Malvina Nissim | 4 | 479 | 51.48 |
Bonnie Lynn Webber | 5 | 1511 | 317.14 |
James R. Curran | 6 | 1764 | 133.42 |