Factoid Question Answering over Unstructured and Structured Web Content

We describe our experience with two new, builtfrom-scratch, web-based question answering systems applied to the TREC 2005 Main Question Answering task, which use complementary models of answering questions over both structured and unstructured content on the Web. Our approaches depart from previous question answering (QA) work in several ways. For unstructured content, we used a web-based system with novel features such as web snippet pattern matching and generic answer type matching using web counts. We also experimented with a new, complementary question answering approach that uses information from the millions of tables and lists that abound on the web. This system attempts to answer factoid questions by guessing relevant rows and fields in matching web tables and integrating the results. We believe a combination of the two approaches holds promise.