Distributional Tensor Space Model of Natural Language Semantics

Eugenie Giesbrecht
We propose a novel Distributional Tensor Space Model of natural language semantics employing 3d order tensors that accounts for order dependent word contexts and assigns to words characteristic matrices such that semantic composition can be realized in a linguistically and cognitively plausible way. The proposed model achieves state-of-the-art results for important tasks of linguistic semantics by using a relatively small text corpus and without any sophisticated preprocessing.
doi:10.5445/ir/1000044671 fatcat:robzu355yzeqtdfqyboiwn5cwm