Semantic QA for encyclopaedic questions: EQUAL in GikiCLEF

Abstract

This paper presents a new question answering (QA) approach and a prototype system, EQUAL, which relies on structural information from Wikipedia to answer open-list questions. The system achieved the highest score amongst the participants in the GikiCLEF 2009 task. Unlike the standard textual QA approach, EQUAL does not rely on identifying the answer within a text snippet by using keyword retrieval. Instead, it explores the Wikipedia page graph, extracting and aggregating information from multiple documents and enforcing semantic constraints. The challenges for such an approach and an error analysis are also discussed. © 2010 Springer-Verlag Berlin Heidelberg.