An Unsupervised Ranking Model for Noun-Noun Compositionality
Karl Moritz Hermann, Phil Blunsom, Stephen Pulman · 2012
We propose an unsupervised system that learns continuous degrees of lexicality for noun-noun compounds, beating a strong baseline on several tasks. We demonstrate that the distributional representations of compounds and their parts can be used to learn a finegrained representation of semantic contribution. Finally, we argue such a representation captures compositionality better than the current status-quo which treats compositionality as a binary classification problem. 1