Easy-First POS Tagging and Dependency Parsing with Beam Search
Ji Ma, Jingbo Zhu, Tong Xiao, Nan Yang · 2013
In this paper, we combine easy-first de-pendency parsing and POS tagging algo-rithms with beam search and structured perceptron. We propose a simple variant of “early-update ” to ensure valid update in the training process. The proposed so-lution can also be applied to combine beam search and structured perceptron with other systems that exhibit spurious ambiguity. On CTB, we achieve 94.01% tagging accuracy and 86.33 % unlabeled attachment score with a relatively small beam width. On PTB, we also achieve state-of-the-art performance. 1