关键词: 英语实体链接, 上下文信息, 排序学习, ListNet排序算法, 实体聚类

Abstract:

English entity linking tasks play an important role in construction of semantic network and big knowledge base. An entity linking method based on local information and learning to rank algorithm was proposed. Firstly, the context information is well used for expanding mentions' name and retrieving candidate entities from Wikipedia. Secondly, kinds of features are extracted between mentions and candidates and also the ListNet algorithm was used to rank the candidate entities to choose the most related entity as the linked objects. Finally, the NIL entities was clustered by clustering method. The method achieved 0.660 F value on KBP 2013 Entity Linking dataset, it performs 0.092 better than the median F value of all participated teams in KBP 2013 entity linking task and also performs 0.162 better than BUPTTeam 2013, which is the baseline comparison system in the experiment.

Key words: English entity linking, context information, learning to rank, ListNet algorithm, entity clustering