Metonymy recognition is generally approached with complex algorithms that rely heavily on the manual annotation of training and test data. This paper will relieve this complexity ...
In this paper a novel solution to automatic and unsupervised word sense induction (WSI) is introduced. It represents an instantiation of the `one sense per collocation' obser...
In recent years tree kernels have been proposed for the automatic learning of natural language applications. Unfortunately, they show (a) an inherent super linear complexity and (...
Probabilistic Latent Semantic Analysis (PLSA) models have been shown to provide a better model for capturing polysemy and synonymy than Latent Semantic Analysis (LSA). However, th...
Given the growing complexity of tasks that spoken dialogue systems are trying to handle, Reinforcement Learning (RL) has been increasingly used as a way of automatically learning ...