A* CCG Parsing with a Supertag and Dependency Factored Model
This work addresses parsing efficiency and accuracy for natural language processing tasks, representing an incremental improvement with specific gains.
The authors tackled the problem of CCG parsing by proposing an A* model that factors probabilities into CCG categories and syntactic dependencies using bi-directional LSTMs, achieving state-of-the-art results on English and Japanese datasets.
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.