Compositional matrix-space models of language.
In:
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, series ACL '10, pages 907-916.
Association for Computational Linguistics, Stroudsburg, PA, USA, 2010.
Sebastian Rudolph and Eugenie Giesbrecht.
[doi]
[abstract]
[BibTeX]
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.