This paper compares two different ways of estimating statistical language models. Many statistical NLP tagging and parsing models are estimated by maximizing the (joint) likelihoo...
Abstract. We build a class-based selection preference sub-model to incorporate external semantic knowledge from two Chinese electronic semantic dictionaries. This sub-model is comb...
We introduce the notion of combinatorial vote, where a group of agents (or voters) is supposed to express preferences and come to a common decision concerning a set of non-independ...
This paper describes a prototype disambiguation module, KANKEI, which was tested on two corpora of the TRAINS project. In ambiguous verb phrases of form V ... NP PP or V ... NP ad...
This paper presents an implemented, psychologicallyplausible parsing model for Government Binding theory grammars. I make use of two main ideas: (1) a generalization of the licens...