UMass CIIR at TAC KBP 2013 Entity Linking: Query Expansion using Urban Dictionary
Jeff Dalton, Laura Dietz · 2013
This paper describes the system submitted to the TAC 2013 entity linking task of the Knowledge Base Population track. The core of the approach is prob-abilistic information retrieval over a search index of the knowledge base, including the text of Wikipedia. The retrieval results are further reranked using a su-pervised learning-to-rank model. The submission this year builds on the neighborhood and context ex-traction methods for query expansion introduced in 2012. In 2013, two new models are added. The first is query expansion using Urban Dictionary. For mentions in forum documents, we search Urban Dic-tionary for the mention string and perform query ex-pansion. The second method is a multi-pass linking model. Instead of linking only the query mention, all entity mentions in the document are linked with fea-tures that encourage coherence among the linked en-tities. The results show that the method incorporat-ing Urban Dictionary expansion run performed the best. 1