Paper: Resolving Lexical Ambiguity in Tensor Regression Models of Meaning

ACL ID P14-2035
Title Resolving Lexical Ambiguity in Tensor Regression Models of Meaning
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

This paper provides a method for improv- ing tensor-based compositional distribu- tional models of meaning by the addition of an explicit disambiguation step prior to composition. In contrast with previous re- search where this hypothesis has been suc- cessfully tested against relatively simple compositional models, in our work we use a robust model trained with linear regres- sion. The results we get in two experi- ments show the superiority of the prior dis- ambiguation method and suggest that the effectiveness of this approach is model- independent.