Measuring Sentences Similarity: A Survey

TL;DR

This survey reviews various methods for measuring sentence similarity in NLP, categorizing approaches into word-to-word, structure, and vector-based, and discusses benchmark datasets and the potential of combined methods.

Contribution

It provides a comprehensive classification of sentence similarity approaches and highlights the need for further research in structure-based methods.

Findings

Combined approaches yield better similarity measurement results.

Structure-based methods require more investigation.

Benchmark datasets are essential for evaluating techniques.

Abstract

This study is to review the approaches used for measuring sentences similarity. Measuring similarity between natural language sentences is a crucial task for many Natural Language Processing applications such as text classification, information retrieval, question answering, and plagiarism detection. This survey classifies approaches of calculating sentences similarity based on the adopted methodology into three categories. Word-to-word based, structure based, and vector-based are the most widely used approaches to find sentences similarity. Each approach measures relatedness between short texts based on a specific perspective. In addition, datasets that are mostly used as benchmarks for evaluating techniques in this field are introduced to provide a complete view on this issue. The approaches that combine more than one perspective give better results. Moreover, structure based similarity that measures similarity between sentences structures needs more investigation.