Evolution of Semantic Similarity -- A Survey

Abstract

Estimating the semantic similarity between text data is one of the challenging and open research problems in the field of Natural Language Processing (NLP). The versatility of natural language makes it difficult to define rule-based methods for determining semantic similarity measures. In order to address this issue, various semantic similarity methods have been proposed over the years. This survey article traces the evolution of such methods, categorizing them based on their underlying principles as knowledge-based, corpus-based, deep neural network-based methods, and hybrid methods. Discussing the strengths and weaknesses of each method, this survey provides a comprehensive view of existing systems in place, for new researchers to experiment and develop innovative ideas to address the issue of semantic similarity.

29 pages, 5 figures, submitted to "ACM Computing Survey"

References in corpus (5)

• Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features
• SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation
• Bridging the Gap: Incorporating a Semantic Similarity Measure for Effectively Mapping PubMed Queries to Documents
• Multi-sense embeddings through a word sense disambiguation process
• Interpretable Semantic Textual Similarity: Finding and explaining differences between sentences

Cited by in corpus (13)

• Reviewing Intelligent Cinematography: AI research for camera-based video production
• Semantic relatedness in DBpedia: A comparative and experimental assessment
• Near-Term Advances in Quantum Natural Language Processing
• The Geometry of Concepts: Sparse Autoencoder Feature Structure
• A Parametric Similarity Method: Comparative Experiments based on Semantically Annotated Large Datasets
• Reviewing Evolution of Learning Functions and Semantic Information Measures for Understanding Deep Learning
• Word Closure-Based Metamorphic Testing for Machine Translation
• A Cognitive Study on Semantic Similarity Analysis of Large Corpora: A Transformer-based Approach
• Semantic Similarity Measure of Natural Language Text through Machine Learning and a Keyword-Aware Cross-Encoder-Ranking Summarizer -- A Case Study Using UCGIS GIS&T Body of Knowledge
• NLP and Education: using semantic similarity to evaluate filled gaps in a large-scale Cloze test in the classroom
• The More Similar, the Better? Associations between Latent Semantic Similarity and Emotional Experiences Differ across Conversation Contexts
• Automating Transfer Credit Assessment in Student Mobility -- A Natural Language Processing-based Approach
• Survey of Genetic and Differential Evolutionary Algorithm Approaches to Search Documents Based On Semantic Similarity