论文信息 - QACTIS-based Question Answering at TREC 2005

QACTIS-based Question Answering at TREC 2005

The QACTIS system is being developed for the eventual purpose of providing a user the capability of multilingual question-answering from multimedia. QACTIS was tested at TREC-2005 as a means of identifying its successes and limitations in answering questions specifically from English newswire text as it moves in the direction of multilingual, multimedia question answering. In this paper, we provide a complete overview of those parts of QACTIS which focus specifically on text question-answering, and we analyze the system’s performance at TREC-2005.

[1] Daniel Jurafsky,et al. Learning Syntactic Patterns for Automatic Hypernym Discovery , 2004, NIPS.

[2] Richard M. Schwartz,et al. An Algorithm that Learns What's in a Name , 1999, Machine Learning.

[3] George A. Miller,et al. Introduction to WordNet: An On-line Lexical Database , 1990 .

[4] James Mayfield,et al. JHU/APL at TREC 2005: QA Retrieval and Robust Tracks , 2005, TREC.

[5] Patrick Schone,et al. Text Retrieval via Semantic Forests , 1997, TREC.

[6] James Mayfield,et al. Question Answering with QACTIS at TREC 2004 , 2004, TREC.

[7] Eugene Charniak,et al. A Maximum-Entropy-Inspired Parser , 2000, ANLP.