ANALYSIS OF LEXICAL, SYNTACTIC AND SEMANTIC FEATURES FOR SEMANTIC TEXTUAL SIMILARITY

Semantic Textual Similarity (STS) calculates the degree of semantic equivalence between two textual snippets, even though they do not share common words. The textual snippets are words, phrases, sentences, paragraphs or documents. In this work, the textual snippets are sentences. The similarity between the sentences can be measured with the aid of lexical, syntactic and semantic features entrenched in the sentences. In SemEval workshop, the STS task is to measure the semantic similarity between the sentence pairs. The dataset contains the sentence pairs and the human annotated real values from 0-5. In this paper, the experimental analysis of various lexical, syntactic and semantic features on STS 2016 dataset is carried out. This analysis is useful while building the models with machine learning algorithms with the aid of these features. The impact of the individual features on semantic textual equivalence is assessed between the feature generated values and human annotated values using Pearson Correlation Coefficient.