English

Concurrent Parsing of Constituency and Dependency

Computation and Language 2019-09-27 v2 Machine Learning

Abstract

Constituent and dependency representation for syntactic structure share a lot of linguistic and computational characteristics, this paper thus makes the first attempt by introducing a new model that is capable of parsing constituent and dependency at the same time, so that lets either of the parsers enhance each other. Especially, we evaluate the effect of different shared network components and empirically verify that dependency parsing may be much more beneficial from constituent parsing structure. The proposed parser achieves new state-of-the-art performance for both parsing tasks, constituent and dependency on PTB and CTB benchmarks.

Keywords

Cite

@article{arxiv.1908.06379,
  title  = {Concurrent Parsing of Constituency and Dependency},
  author = {Junru Zhou and Shuailiang Zhang and Hai Zhao},
  journal= {arXiv preprint arXiv:1908.06379},
  year   = {2019}
}

Comments

arXiv admin note: text overlap with arXiv:1907.02684

R2 v1 2026-06-23T10:49:59.260Z