Resolving Lexical Ambiguity in Tensor Regression Models of Meaning
This addresses lexical ambiguity in natural language processing for improved semantic modeling, but it is incremental as it builds on prior disambiguation research with a more robust model.
The paper tackles the problem of lexical ambiguity in tensor-based compositional distributional models of meaning by adding an explicit disambiguation step before composition, showing superiority of this method in two experiments and suggesting its model-independent effectiveness.
This paper provides a method for improving tensor-based compositional distributional models of meaning by the addition of an explicit disambiguation step prior to composition. In contrast with previous research where this hypothesis has been successfully tested against relatively simple compositional models, in our work we use a robust model trained with linear regression. The results we get in two experiments show the superiority of the prior disambiguation method and suggest that the effectiveness of this approach is model-independent.