This paper proposes a new method for automatic acquisition of Chinese bracketing knowledge from English-Chinese sentencealigned bilingual corpora. Bilingual sentence pairs are fir...
How should a reinforcement learning agent act if its sole purpose is to efficiently learn an optimal policy for later use? In other words, how should it explore, to be able to exp...
In 2004, ISO/IEC SC29 better known as MPEG started a new standard initiative aiming at facilitating the deployment of multi-format video codec design and to enable the possibility...
Exploiting unannotated natural language data is hard largely because unsupervised parameter estimation is hard. We describe deterministic annealing (Rose et al., 1990) as an appea...
We present a novel approach for building verb subcategorization lexicons using a simple graphical model. In contrast to previous methods, we show how the model can be trained with...
Thomas Lippincott, Anna Korhonen, Diarmuid Ó...