Word Embeddings for Unsupervised Named Entity Linking


The huge amount of textual user-generated content on the Web has incredibly grown in the last decade, creating new relevant opportunities for different real-world applications and domains. In particular, microblogging platforms enables the collection of continuously and instantly updated information. The organization and extraction of valuable knowledge from these contents are fundamental for ensuring profitability and efficiency to companies and institutions. This paper presents an unsupervised model for the task of Named Entity Linking in microblogging environments. The aim is to link the named entity mentions in a text with their corresponding knowledge-base entries exploiting a novel heterogeneous representation space characterized by more meaningful similarity measures between words and named entities, obtained by Word Embeddings. The proposed model has been evaluated on different benchmark datasets proposed for Named Entity Linking challenges for English and Italian language. It obtains very promising performance given the highly challenging environment of user-generated content over microblogging platforms.