Overview of the INEX 2010 Link the Wiki Track

摘要

The INEX 2010 Link-the-Wiki track examined link-discovery in the Te Ara collection, a previously unlinked document collection. Te Ara is structured more a digital cultural history than as a set of entities. With no links and no automatic entity identification, previous Link-the-Wiki algorithms could not be used. Assessment was also necessarily manual. In total 29 runs were submitted by 2 institutes. 70 topics were assessed, but only 52 had relevant target documents and only 45 had relevant links in the pool. This suggests that the pool was not diverse enough. The best performing run had a MAP of less than 0.1 suggesting that the algorithms tested in 2010 were not very effective.