Aligning Packed Dependency Trees: a theory of composition for distributional semantics

TL;DR

This paper introduces a novel framework for compositional distributional semantics using anchored packed dependency trees, enabling better sentence-level meaning representation and capturing disambiguation and generalization.

Contribution

It proposes a new structure for distributional semantics that unifies context representation and compositionality through dependency trees.

Findings

Potential to capture full sentential contexts of lexemes

Provides a uniform basis for composition of distributional knowledge

Captures mutual disambiguation and generalization

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.