English

Hierarchical Pointer Net Parsing

Computation and Language 2022-10-21 v1 Machine Learning

Abstract

Transition-based top-down parsing with pointer networks has achieved state-of-the-art results in multiple parsing tasks, while having a linear time complexity. However, the decoder of these parsers has a sequential structure, which does not yield the most appropriate inductive bias for deriving tree structures. In this paper, we propose hierarchical pointer network parsers, and apply them to dependency and sentence-level discourse parsing tasks. Our results on standard benchmark datasets demonstrate the effectiveness of our approach, outperforming existing methods and setting a new state-of-the-art.

Keywords

Cite

@article{arxiv.1908.11571,
  title  = {Hierarchical Pointer Net Parsing},
  author = {Linlin Liu and Xiang Lin and Shafiq Joty and Simeng Han and Lidong Bing},
  journal= {arXiv preprint arXiv:1908.11571},
  year   = {2022}
}

Comments

Accepted by EMNLP 2019

R2 v1 2026-06-23T11:00:41.715Z