Abstract | ||
---|---|---|
We describe recent extensions to the Ephyra question answer- ing (QA) system and their evaluation in the TREC 2007 QA track. Existing syntactic answer extraction approaches for factoid and list questions have been complemented with a high-accuracy semantic approach that generates a semantic representation of the question and extracts answer candidates from similar semantic structures in the corpus. Candidates found by different answer extractors are combined and ranked by a statistical framework that integrates a variety of answer validation techniques and similarity measures to estimate a probability for each candidate. A novel answer type classi- fier combines a statistical model and hand-coded rules to pre- dict the answer type based on syntactic and semantic features of the question. Our approach for the 'other' questions uses Wikipedia and Google to judge the relevance of answer can- didates found in the corpora. |
Year | Venue | Keywords |
---|---|---|
2007 | TREC | statistical model |
Field | DocType | Citations |
Data mining,Question answering,Information retrieval,Ranking,Computer science,Natural language processing,Statistical model,Artificial intelligence,Classifier (linguistics),Semantic representation,Syntax,Factoid | Conference | 30 |
PageRank | References | Authors |
1.85 | 22 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nico Schlaefer | 1 | 559 | 26.50 |
Jeongwoo Ko | 2 | 176 | 14.11 |
Justin Betteridge | 3 | 238 | 11.95 |
Manas Pathak | 4 | 30 | 2.19 |
Eric Nyberg | 5 | 1110 | 101.91 |
Guido Sautter | 6 | 67 | 8.00 |