A Comprehensive Comparative Study of Word and Sentence Similarity Measures
This provides a systematic evaluation for researchers in natural language processing, but it is incremental as it reviews and compares existing methods.
The paper conducted a comparative study of word and sentence similarity measures on benchmark datasets, finding that hybrid semantic measures outperformed knowledge-based and corpus-based approaches.
Sentence similarity is considered the basis of many natural language tasks such as information retrieval, question answering and text summarization. The semantic meaning between compared text fragments is based on the words semantic features and their relationships. This article reviews a set of word and sentence similarity measures and compares them on benchmark datasets. On the studied datasets, results showed that hybrid semantic measures perform better than both knowledge and corpus based measures.