Aligning Packed Dependency Trees: a theory of composition for distributional semantics
Computation and Language
2016-08-26 v1
Abstract
We present a new framework for compositional distributional semantics in which the distributional contexts of lexemes are expressed in terms of anchored packed dependency trees. We show that these structures have the potential to capture the full sentential contexts of a lexeme and provide a uniform basis for the composition of distributional knowledge in a way that captures both mutual disambiguation and generalization.
Keywords
Cite
@article{arxiv.1608.07115,
title = {Aligning Packed Dependency Trees: a theory of composition for distributional semantics},
author = {David Weir and Julie Weeds and Jeremy Reffin and Thomas Kober},
journal= {arXiv preprint arXiv:1608.07115},
year = {2016}
}
Comments
To appear in Special issue of Computational Linguistics - Formal Distributional Semantics