Abstract
High impact events, political changes and new technologies are reflected in our language and lead to constant evolution of terms, expressions and names. This makes search using standard search engines harder, as users need to know all different names used over time to formulate an appropriate query. The fokas search engine demonstrates the impact of enriching search results with results for all temporal variants of the query. It uses NEER, a method for named entity evolution recognition. For each query term, NEER detects temporal variants and presents these to the user. A chart with term frequencies helps users choose among the proposed names to extend the query. This extended query captures relevant documents using temporal variants of the original query and improves overall quality. We use the New York Times corpus which, with its 20 year timespan and many name changes, constitutes a good collection to demonstrate NEER and fokas.
Users
Please
log in to take part in the discussion (add own reviews or comments).