English

A* CCG Parsing with a Supertag and Dependency Factored Model

Computation and Language 2017-04-25 v1

Abstract

We propose a new A* CCG parsing model in which the probability of a tree is decomposed into factors of CCG categories and its syntactic dependencies both defined on bi-directional LSTMs. Our factored model allows the precomputation of all probabilities and runs very efficiently, while modeling sentence structures explicitly via dependencies. Our model achieves the state-of-the-art results on English and Japanese CCG parsing.

Keywords

Cite

@article{arxiv.1704.06936,
  title  = {A* CCG Parsing with a Supertag and Dependency Factored Model},
  author = {Masashi Yoshikawa and Hiroshi Noji and Yuji Matsumoto},
  journal= {arXiv preprint arXiv:1704.06936},
  year   = {2017}
}

Comments

long paper (11 pages) accepted to ACL 2017