Bhilai Institute of Technology Durg at TAC 2010: Knowledge Base Population Task Challenge

The present communication aims to report the TAC forum about the system-incorporated towards Entity-Linking task. The noun-phrases relevant to the search term were used to correlate the entityrelevant happenings mentioned in the source documents to that of the entity-relevant information in the knowledge-base. Care was taken in identifying the abbreviation and full form variants of search names if present in the same set of queries or in the provided Knowledge base as Wikipedia structured nodes. The subsequent knowledge-base node hits led to the ranking of their respective content for retrieving entity-linking node-id responses. Three different runs were submitted the Task Challenge following the different ways to search for the most meaningfully relevant information about the entities mentioned in Entity-Linking Target list from the Knowledge-base of the track. The team’s spirits feels elevated at the thought of using the free text from the Wikipedia pages associated with the knowledge base nodes, while building the evaluation model as it adds to the robustness and reliability of the system even at the time of inaccessibility of the Web.