EQUAL: Encyclopaedic QUestion Answering for Lists

This paper presents EQUAL , a semantic question answering (QA) system which relies on structural information from Wikipedia to extract answers to list questions in the GikiCLEF 2009 task. The system is described in the context of of a more general architecture for semantic QA. Unlike the usual 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. Enforcing semantic constraints proved to yield precise results, and the system achieved the highest score amongst the participants in the task.