Geometry of Compositionality

Understand

This paper proposes a simple test for compositionality (i.e., literal usage) of a word or phrase in a context-specific way.

• The test is computationally simple, relying on no external resources and only uses a set of trained word vectors.
• Experiments show that the proposed method is competitive with state of the art and displays high accuracy in context-specific compositionality detection of a variety of natural language phenomena (idiomaticity, sarcasm, metaphor) for different datasets in multiple languages.
• The key insight is to connect compositionality to a curious geometric property of word embeddings, which is of independent interest.