Sentence representations for semantic textual similarity: A systematic review

In natural language processing (NLP), generating semantically-rich representations of sentences can improve performance on multiple tasks, such as question answering, duplicate detection, sentiment analysis, and machine translation. Recent approaches to NLP using machine learning can produce text representations that carry syntactic and semantic information. This article surveys recent works on generating sentence representations for semantic textual similarity tasks. We conduct our survey using a systematic literature review approach. We retrieve papers from several digital libraries and summarize their key techniques and findings. We propose a taxonomy to facilitate the understanding of the semantic textual similarity task on the sentence level. In our analysis, we describe the current state-of-the-art in sentence representation for semantic textual similarity and propose a guideline for working on this task. • Identification of the main research on semantic similarity between sentences. • Taxonomy to define the field of semantic similarity. • Identification of state-of-the-art approaches for existing datasets. • Guidelines for working on semantic similarity between sentences.