Author(s): Hawre Hosseini, Tam T. Nguyen, Ebrahim Bagheri
Abstract: The systematic linking of phrases within a document to entities of a knowledge base has already been explored in a process known as entity linking. The underlying idea of these methods is to unambiguously determine whether or not a phrase is referring to some entity within a knowledge base and as such the assumption is that the entity being described is explicitly mentioned. The objective of this paper; however, is to identify and entity link those entities that are not mentioned but are implied within a document, more specifically within a tweet in this paper. This process is referred to as implicit entity linking. Unlike prior work that build a representation for each entity based on its related content in the knowledge base, we propose to perform implicit entity linking by determining how a tweet is related to user-generated content posted online and as such indirectly perform entity linking. We formulate this problem as an ad hoc document retrieval process where the input query is the tweet, which needs to be implicitly linked and the document space is the set of user-generated content related to the entities of the knowledge base. The novel contributions of our work include: 1) defining the implicit entity linking process as an ad hoc document retrieval task; and 2) proposing a neural embedding-based feature function that is interpolated with prior term dependency and entity-based feature functions. We systematically compare our work with the state of the art baseline and show that our method is able to provide statistically significant improvements.
Keywords: Entity linking; Semantic retrieval; DBpedia; Knowledge graph