Rev at SemEval-2016 task 2: Aligning chunks by lexical, part of speech and semantic equivalence

Abstract

We present the description of our submission to SemEval-2016 Task 2, for the sub-task of aligning pre-annotated chunks between sentence pairs and providing similarity and relat-edness labels for the alignment. The objective of the task is to provide interpretable semantic textual similarity assessments by adding an explanatory layer to aligned chunks. We analysed the provided datasets, considering lexical overlap, the part of speech tags and the synonyms of the words in the chunks, and developed a rule-based system reflecting that analysis. Our system performance indicates that when sentence pairs are similar, alignment of chunks can be performed fairly well using lexical information alone without syntactic or semantic analysis. The advantage of our system is that we can easily trace when chunks are aligned.