Building on Redundancy Factoid Question Answering, Robust Retrieval and the “Other”.pdf

Building on Redundancy: Factoid Question Answering, Robust Retrieval and the “Other” Dmitri Roussinov Michael Chau Arizona State University School of Business Department of Information Systems The University of Hong Kong Dmitri.Roussinov@ mchau@business.hku.hk Elena Filatova José Antonio Robles-Flores Columbia University Arizona State University/ESAN Department of Computer Science Department of Information Systems filatova@ Jose.Robles@ ABSTRACT We have explored how redundancy based techniques can be used in improving factoid question answering, definitional questions (“other”), and robust retrieval. For the factoids, we explored the meta approach: we submit the questions to the several open domain question answering systems available on the Web and applied our redund ancy-based triangulation algorithm to analyze their outputs in order to identify the most promising answers. Our results support the added value of the meta approach: the performance of the combined system surpassed the underlying performances of its components. To answer definitional (“other”) questions, we were looking for the sentences containing re -occurring pairs of noun entities containing the elements of the target. For robust retrieval, we applied our redundancy based Internet mining technique to identify th