The QUANTUM Question Answering System at TREC 11.

作者: Leila Kosseim , Guy Lapalme , Luc Plamondon

DOI:

关键词:

摘要: This year, we participated to the Question Answering task for second time with QUANTUM system. We entered 2 runs main (one using web, other without) and 1 run list (without web). essentially built on last year’s experience enhance The architecture of is mainly same as year: it uses patterns that rely shallow parsing techniques regular expressions analyze question then select most appropriate extraction function. function applied one-paragraph long passages retrieved by Okapi extract score candidate answers. Among novelties added this year a web module finds exact answers high-precision reformulation anticipate expected context

参考文章(5)
Leila Kosseim, Guy Lapalme, Luc Plamondon, The QUANTUM Question Answering System. text retrieval conference. pp. 579- 585 ,(2001)
Susan T. Dumais, Andrew Y. Ng, Michele Banko, Jimmy J. Lin, Eric Brill, Data-intensive Question Answering text retrieval conference. pp. 393- 400 ,(2001)
Luc Plamondon, Leila Kosseim, QUANTUM: A Function-Based Question Answering System Lecture Notes in Computer Science. pp. 281- 292 ,(2002) , 10.1007/3-540-47922-8_23
Stephen E. Robertson, Steve Walker, Okapi/Keenbow at TREC-8. text retrieval conference. pp. 151- 162 ,(1999)
G. L. McLearn, Thomas R. Lynam, Charles L. A. Clarke, Gordon V. Cormack, C. M. Li, Web Reinforced Question Answering (MultiTest Experiments for TREC 2001). text retrieval conference. pp. 673- 679 ,(2001)