This report describes the system developed by the University of Edinburgh and the University 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 experimented with external sources of knowledge, such as Google and Wikipedia, to enhance the performance of QED, especially for reranking and off-line processing of the corpus. For factoid and list questions we performed significantly above the median accuracy score of all participating systems at TREC 2005.
Ahn K., Bos J., Curran J., Kor D., Nissim M., Webber B. (2005). Question Answering with QED at TREC-2005. U.S. GOVERNMENT : NIST.
Question Answering with QED at TREC-2005
NISSIM, MALVINA;
2005
Abstract
This report describes the system developed by the University of Edinburgh and the University 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 experimented with external sources of knowledge, such as Google and Wikipedia, to enhance the performance of QED, especially for reranking and off-line processing of the corpus. For factoid and list questions we performed significantly above the median accuracy score of all participating systems at TREC 2005.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
