BIT and MSRA at TREC KBA CCR Track 2013
Jingang Wang, Dandan Song, Lejian Liao, Chin-Yew Lin · Text REtrieval Conference · 2013
Our strategy for TREC KBA CCR track is to rst retrieve as many vital or documents as possible and then apply more sophisticated classication and ranking methods to dierentiate vital from useful documents. We submitted 10 runs generated by 3 approaches: question expansion, classication and learning to rank. Query expansion is an unsupervised baseline, in which we combine entities’ names and their related entities’ names as phrase queries to retrieve relevant documents. This baseline outperforms the overall median and mean submissions. The system performance is further improved by supervised classication and learning to