Question Answering Performance on Table Data

Question answering (QA) on table data is a challenging information retrieval task. This paper describes a QA system for tables created with both machine learning and heuristic table extraction methods. Errors were analyzed in order to improve the system using government statistical data. We also apply these improvements on another type of table data set and show the experimental results.

• Type: Conference
• Year: 2004
• Where: DGO
• Authors: Xing Wei, W. Bruce Croft, David Pinto
• Keywords: Challenging Information Retrieval, DGO 2004, DGO 2007, Heuristic Table Extraction, Table Data