QA UdG-UPC System at TREC-12.
作者： Daniel Ferrés , Horacio Rodríguez , Marc Massot
DOI:
关键词: Task (project management) 、 EuroWordNet 、 Information retrieval 、 Cluster analysis 、 Computer science 、 Factoid 、 Inductive programming 、 Natural language processing 、 Artificial intelligence 、 Inductive logic programming
摘要: This paper describes a prototype multilingual Q&A system that we have designed to participate in the Track of TREC-12. The answer concrete responses, then main task for factoid questions. areas our are: (1) Inductive Logic Programming learn question type, (2) Clustering Named Entities improve Information Retrieval and (3) Semantic relations EuroWordNet synsets perform language-independent extraction.
参考文章(4)
Bernardo Magnini, Gabriela Cavaglia, Integrating Subject Field Codes into WordNet language resources and evaluation. ,(2000)
Dekang Lin, Dependency-Based Evaluation of Minipar Treebanks. pp. 317- 329 ,(2003) , 10.1007/978-94-010-0201-1_18
J. R. Quinlan, R. M. Cameron-Jones, FOIL: A Midterm Report european conference on machine learning. pp. 3- 20 ,(1993) , 10.1007/3-540-56602-3_124
Xavier Carreras, Lluís Màrquez, Lluís Padró, Named Entity Extraction using AdaBoost international conference on computational linguistics. pp. 1- 4 ,(2002) , 10.3115/1118853.1118857