A semantic similarity measure based on lexico-syntactic patterns

Conclusion Performance on human judgement (MC, RG, WS) and semantic relation (BLESS and SN) datasets We present a novel semantic similarity measure based on lexico-syntactic patterns such as those proposed by Hearst (1992). The measure achieves a correlation with human judgements up to 0.739. Additionally, we evaluate it on the tasks of semantic relation ranking and extraction. Our results show that the measure provides results comparable to the baselines without the need for any fine-grained semantic resource such as WordNet.