Towards holistic Entity Linking: Survey and directions

Entity Linking (EL) empowers Natural Language Processing applications by linking relevant mentions found in raw textual data to precise information about what they supposedly stand for. However, EL approaches have mostly focused on particular kinds of inputs and frequently fail to properly handle texts from specific sources (e.g., microblogs) that have particularities such as grammatical errors, slangs, lack of contextual information and other problems, besides difficulties to exploit their associated data (e.g., time stamps, geographic indicators, authors' profile data). Some EL approaches have been devised to circumvent such challenges. They exploit several inputs, data features, and EL methods in a synergetic process for more powerful and robust collective EL. This paper reviews recent works that employ such holistic strategies for EL, discusses their limitations, and proposes directions for further advancing holistic EL approaches.