Easy-First POS Tagging and Dependency Parsing with Beam Search
Ji Ma, Jingbo Zhu, Tong Xiao and Nan Yang
The 51st Annual Meeting of the Association for Computational Linguistics - Short Papers (ACL Short Papers 2013)
Sofia, Bulgaria, August 4-9, 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 94.11% tagging accuracy and 86.33% unlabeled attachment score with a relatively small beam width. On PTB, we also achieve state-of-the-art performance.
Conference Manager (V2.61.0 - Rev. 2792M)