Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?

摘要：

　　In the pre deep learning era,part-of-speech tags have been considered as indispensable ingredients for feature engineering in depen-dency parsing.But quite a few works focus on joint tagging and parsing models to avoid error propagation.In contrast,recent studies suggest that POS tagging becomes much less important or even useless for neural parsing,especially when using character-based word representations.Yet there are not enough investigations focusing on this issue,both empir-ically and linguistically.To answer this,we design and compare three typical multi-task learning framework,i.e.,Share-Loose,Share-Tight,and Stack,for joint tagging and parsing based on the state-of-the-art biaffine parser.Considering that it is much cheaper to annotate POS tags than parse trees,we also investigate the utilization of large-scale heterogeneous POS tag data.We conduct experiments on both English and Chinese datasets,and the results clearly show that POS tagging(both homogeneous and heterogeneous)can still significantly improve parsing performance when using the Stack joint framework.We conduct detailed analysis and gain more insights from the linguistic aspect.

作者: Houquan Zhou Yu Zhang Zhenghua Li Min Zhang

作者单位: Institute of Artificial Intelligence,School of Computer Science and Technology,Soochow University,Suzhou,China

会议类型: 国际会议

会议名称: 9th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2020)

会议地点: 郑州

会议语种:英文

页码: 179-191

在线出版日期: 2020-10-14（万方平台首次上网日期，不代表论文的发表时间）