Both semantic representation and related natural language processing(NLP) tasks has become more popular due to the introduction of distributional semantics. Semantic textual similarity (STS)is one of a task in NLP, it determinesthe similarity based onthe meanings of two shorttexts (sentences). Interpretable STS is the way of giving explanation to semantic similarity between short texts. Giving interpretation is indeedpossible tohuman, but, constructing computational modelsthat explain as human level is challenging. The interpretable STS task give output in natural way with a continuous value on the scale from [0, 5] that represents the strength of semantic relation between pair sentences, where 0 is no similarity and 5 is complete similarity. This paper review all available methods were used in interpretable STS computation, classify them, specifyan existing limitations, and finally give directions for future work. This paper is organized the survey into nine sections as follows: firstly introduction at glance, then chunking techniques and available tools, the next one is rule based approach, the fourth section focus on machine learning approach, after that about works done via neural network, and the finally hybrid approach concerned. Application of interpretable STS, conclusion and future direction is also part of this paper.