Short-Text Semantic Similarity (STSS): Techniques, Challenges and Future Perspectives

In natural language processing, short-text semantic similarity (STSS) is a very prominent field. It has significant impact on broad range of applications, such as question–answering systems, information retrieval, entity recognition, text analytics, sentiment classification, and so on. Despite their widespread use, many traditional machine learning techniques are incapable identifying the semantics short text. Traditional methods based ontologies, knowledge graphs, corpus-based methods. The performance these influenced by manually defined rules. Applying measures still difficult, since it poses various challenges. existing literature, most recent advances in research not included. This study presents systematic literature review (SLR) with aim to (i) explain sentence barriers similarity, (ii) identify appropriate standard deep for text, (iii) classify models that produce high-level contextual information, (iv) determine datasets only intended (v) highlight challenges proposed future improvements. To best our knowledge, we have provided an in-depth, comprehensive, trends, which will assist researchers reuse enhance information.