Applying Textual Entailment to the Interpretation of Metaphor

Metaphor is a pervasive feature of human language that enables us to conceptualize and communicate abstract concepts using more concrete terminology. Unfortunately, computational models of natural language understanding - including systems for question answering, textual entailment, lexical substitution, and word-sense disambiguation - are unable to appropriately grasp the semantic content of metaphor and other forms of figurative language. In particular, we address the problem of understanding metaphoric language in the context of entailment (or paraphrase) detection. We build upon our existing state-of-the-art textual entailment system to specifically address issues of lexical entailment within a metaphoric context and have performed an in-depth experimental analysis to determine which techniques are most effective at interpreting metaphorical text. Our results suggest that a machine learning system trained on metaphor-rich data can achieve an accuracy above 90% for verbal metaphors using a combination of lexical, semantic, and contextual measures of term similarity.