Information Review Measurement of Text Similarity: a survey Jiapeng Wang and Yihong Dong

Document Outline

• Introduction 
• Text Distance 
  • Length Distance 
    • Euclidean Distance 
    • Cosine Distance 
    • Manhattan Distance 
    • Hamming Distance 
  • Distribution Distance 
    • JS Divergence 
    • KL Divergence 
    • Wasserstein Distance 
  • Semantic Distance 
    • Word Mover’s Distance 
    • Word Mover’s Distance Extension 
• Text Representation 
  • String-Based 
    • Character-Based 
    • Phrase-Based 
  • Corpus-Based 
    • Bag-of-Words Model 
    • Shallow Window-Based Methods 
    • Matrix Factorization Methods 
  • Semantic Text Matching 
    • Single Semantic Text Matching 
    • Multi-Semantic Document Matching 
  • Based on Graph Structure 
    • Knowledge Graph 
    • Graph Neural Network 
• Discussion 
• Conclusions 
• References