| Title | Accelerating Graph-Based Dependency Parsing with Lock-Free Parallel Perceptron |
| Authors | Ma, Shuming Sun, Xu Zhang, Yi Wei, Bingzhen |
| Affiliation | MOE Key Lab of Computational Linguistics, School of EECS, Peking University, Beijing, China |
| Issue Date | 2018 |
| Publisher | 7th CCF International Conference on Natural Language Processing and Chinese Computing, NLPCC 2018 |
| Citation | 7th CCF International Conference on Natural Language Processing and Chinese Computing, NLPCC 2018. 2018, 11108 LNAI, 260-268. |
| Abstract | 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. © 2018, Springer Nature Switzerland AG. |
| URI | http://hdl.handle.net/20.500.11897/530700 |
| ISSN | 9783319994949 |
| DOI | 10.1007/978-3-319-99495-6_22 |
| Indexed | EI |
| Appears in Collections: | 信息科学技术学院 计算语言学教育部重点实验室 |
