DEEP LEARNING FOR SEMANTIC MATCHING: A SURVEY

Authors

  • Han Li University of Wisconsin-Madison
  • Yash Govind University of Wisconsin-Madison
  • Sidharth Mudgal University of Wisconsin-Madison
  • Theodoros Rekatsinas University of Wisconsin-Madison
  • AnHai Doan University of Wisconsin-Madison

DOI:

https://doi.org/10.15625/1813-9663/37/4/16151

Abstract

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.

Downloads

Published

2021-10-12

Issue

Section

SPECIAL ISSUE DEDICATED TO THE MEMORY OF PROFESSOR PHAN DINH DIEU - PART B