Compositional matrix-space models of language
Rudolph, S. & Giesbrecht, E.
, 'Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics', ACL '10, Association for Computational Linguistics, Stroudsburg, PA, USA, 907-916 (2010) [pdf]
We propose CMSMs, a novel type of generic compositional models for syntactic and semantic aspects of natural language, based on matrix multiplication. We argue for the structural and cognitive plausibility of this model and show that it is able to cover and combine various common compositional NLP approaches ranging from statistical word space models to symbolic grammar formalisms.