Geometry of Compositionality
Computation and Language
2016-11-30 v1
Abstract
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.
Cite
@article{arxiv.1611.09799,
title = {Geometry of Compositionality},
author = {Hongyu Gong and Suma Bhat and Pramod Viswanath},
journal= {arXiv preprint arXiv:1611.09799},
year = {2016}
}