Aligning Packed Dependency Trees: a theory of composition for distributional semantics
This work addresses the challenge of semantic composition in natural language processing, offering a novel approach for researchers in computational linguistics.
The authors tackled the problem of compositional distributional semantics by introducing a framework using anchored packed dependency trees to capture full sentential contexts of lexemes, resulting in a method that enables mutual disambiguation and generalization.
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.