Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training
AACL/IJCNLP(2020)
摘要
In this paper, we propose second-order graph-based neural dependency parsing using message passing and end-to-end neural networks. We empirically show that our approaches match the accuracy of very recent state-of-the-art second-order graph-based neural dependency parsers and have significantly faster speed in both training and testing. We also empirically show the advantage of second-order parsing over first-order parsing and observe that the usefulness of the head-selection structured constraint vanishes when using BERT embedding.
更多查看译文
关键词
message passing,second-order,end-to-end
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络