Semantic Similarity and Textual Entailment
Rohit Gupta, Hanna B ́ echara · 2014
This paper presents the system submitted by University of Wolverhampton for SemEval-2014 task 1. We proposed a machine learning approach which is based on features extracted using Typed Dependencies, Paraphrasing, Machine Translation evaluation metrics, Quality Estimation metrics and Corpus Pattern Analysis. Our system performed satisfactorily and obtained 0.711 Pearson correlation for the semantic relatedness task and 78.52% accuracy for the textual entailment task.