Open AccessDEEP LEARNING FOR SEMANTIC MATCHING: A SURVEY
Author(s) -
Lei Han,
Yash Govind,
Sidharth Mudgal,
Θεόδωρος Ρεκατσίνας,
AnHai Doan
Publication year - 2021
Publication title -
journal of computer science and cybernetics (vietnam academy of science and technology)/journal of computer science and cybernetics
Language(s) - English
Resource type - Journals
eISSN - 2815-5939
pISSN - 1813-9663
DOI - 10.15625/1813-9663/37/4/16151
Subject(s) - computer science , schema matching , semantic matching , semantic similarity , information retrieval , coreference , semantic web , semantic web stack , matching (statistics) , artificial intelligence , social semantic web , semantic search , natural language processing , categorization , schema (genetic algorithms) , semantic computing , semantic grid , semantic analytics , semantic heterogeneity , ontology alignment , resolution (logic) , data integration , upper ontology , data mining , ontology based data integration , mathematics , statistics
Semantic matching finds certain types of semantic relationships among schema/data constructs. Examples include entity matching, entity linking, coreference resolution, schema/ontology matching, semantic text similarity, textual entailment, question answering, tagging, etc. Semantic matching has received much attention in the database, AI, KDD, Web, and Semantic Web communities. Recently, many works have also applied deep learning (DL) to semantic matching. In this paper we survey this fast growing topic. We define the semantic matching problem, categorize its variations into a taxonomy, and describe important applications. We describe DL solutions for important variations of semantic matching. Finally, we discuss future R\&D directions.