We introduce into the classical Perceptron algorithm with margin a mechanism of unlearning which in the course of the regular update allows for a reduction of possible contributio...
This paper shows that discriminative reranking with an averaged perceptron model yields substantial improvements in realization quality with CCG. The paper confirms the utility of...
This paper describes a new hybrid architecture for an artificial neural network classifier that enables incremental learning. The learning algorithm of the proposed architecture d...
In this paper, we describe a new reranking strategy named word lattice reranking, for the task of joint Chinese word segmentation and part-of-speech (POS) tagging. As a derivation...
In theory, the Winnow multiplicative update has certain advantages over the Perceptron additive update when there are many irrelevant attributes. Recently, there has been much eff...