Paper: Automatic Selection of Reference Pages in Wikipedia for Improving Targeted Entities Disambiguation

ACL ID E14-4021
Title Automatic Selection of Reference Pages in Wikipedia for Improving Targeted Entities Disambiguation
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

In Targeted Entity Disambiguation setting, we take (i) a set of entity names which be- long to the same domain (target entities), (ii) candidate mentions of the given enti- ties which are texts that contain the tar- get entities as input, and then determine which ones are true mentions of ?target entity?. For example, given the names of IT companies, including Apple, we deter- mine Apple in a mention denotes an IT company or not. Prior work proposed a graph based model. This model ranks all candidate mentions based on scores which denote the degree of relevancy to target entities. Furthermore, this graph based model could utilize reference pages of tar- get entities. However, human annotators must select reference pages in advance. We propose an automatic method that can select reference p...