Compositional Matrix-Space Models of Language

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.

• Type: Journal
• Year: 2010
• Where: ACL
• Authors: Sebastian Rudolph, Eugenie Giesbrecht
• Keywords: ACL 2010, Common Compositional Nlp, Computational Linguistics, Generic Compositional Models, Symbolic Grammar Formalisms