Paper: Towards a Matrix-based Distributional Model of Meaning

ACL ID N10-3005
Title Towards a Matrix-based Distributional Model of Meaning
Venue Proceedings of the NAACL HLT 2010 Student Research Workshop
Session
Year 2010
Authors

Vector-based distributional models of semantics have proven useful and adequate in a variety of natural language processing tasks. How- ever, most of them lack at least one key requirement in order to serve as an adequate representa- tion of natural language, namely sensitivity to structural information such as word order. We propose a novel approach that offers a poten- tial of integrating order-dependent word contexts in a completely un- supervised manner by assigning to words characteristic distributional matrices. The proposed model is applied to the task of free associa- tions. In the end, the first results as well as directions for future work are discussed.