Metaphor Interpretation Using Word Embeddings

TL;DR

This paper presents a novel approach for interpreting metaphors using word embeddings, generating ranked interpretations from corpus data and human association norms, with promising initial results.

Contribution

It introduces a new model that combines corpus-based collocations and human association data for metaphor interpretation using word embeddings.

Findings

Effective ranking of metaphor interpretations based on semantic similarity.

Incorporation of human association norms improves candidate diversity.

Preliminary evaluation shows encouraging results.

Abstract

We suggest a model for metaphor interpretation using word embeddings trained over a relatively large corpus. Our system handles nominal metaphors, like "time is money". It generates a ranked list of potential interpretations of given metaphors. Candidate meanings are drawn from collocations of the topic ("time") and vehicle ("money") components, automatically extracted from a dependency-parsed corpus. We explore adding candidates derived from word association norms (common human responses to cues). Our ranking procedure considers similarity between candidate interpretations and metaphor components, measured in a semantic vector space. Lastly, a clustering algorithm removes semantically related duplicates, thereby allowing other candidate interpretations to attain higher rank. We evaluate using different sets of annotated metaphors, with encouraging preliminary results.