资源分类
》 资源 》论文》An Empirical Investigation of Structured Output Modelingfor Graph-based Neural Dependency Parsing

An Empirical Investigation of Structured Output Modelingfor Graph-based Neural Dependency Parsing

2019-09-18 | |  129 |   51 |   0 0 0
Abstract In this paper, we investigate the aspect of structured output modeling for the state-ofthe-art graph-based neural dependency parser (Dozat and Manning, 2017). With evaluations on 14 treebanks, we empirically show that global output-structured models can generally obtain better performance, especially on the metric of sentence-level Complete Match. However, probably because neural models already learn good global views of the inputs, the improvement brought by structured output modeling is modest.

上一篇：AdaNSP: Uncertainty-driven Adaptive Decoding inNeural Semantic Parsing

下一篇：An Imitation Learning Approach to Unsupervised Parsing

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...