A* CCG Parsing with a Supertag and Dependency Factored Model

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.

arXiv commentlong paper (11 pages) accepted to ACL 2017

References in corpus (4)

• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• DyNet: The Dynamic Neural Network Toolkit
• Structured Training for Neural Network Transition-Based Parsing

Cited by in corpus (5)

• Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP
• The Parallel Meaning Bank: A Framework for Semantically Annotating Multiple Languages
• Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks
• Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference
• Acquisition of Phrase Correspondences using Natural Deduction Proofs