Dependency parsing is an important NLP task. A popular approach for dependency parsing is structured perceptron. Still, graph-based dependency parsing has the time complexity of O(n3), and it suffers from slow training. To deal with this problem, we propose a parallel algorithm called parallel perceptron. The parallel algorithm can make full use of a multi-core computer which saves a lot of training time. Based on experiments we observe that dependency parsing with parallel perceptron can achieve 8-fold faster training speed than traditional structured perceptron methods when using 10 threads, and with no loss at all in accuracy.
@article{arxiv.1703.00782,
title = {Lock-Free Parallel Perceptron for Graph-based Dependency Parsing},
author = {Xu Sun and Shuming Ma},
journal= {arXiv preprint arXiv:1703.00782},
year = {2017}
}