A* CCG Parsing with a Supertag and Dependency Factored Model
A* CCG Parsing with a Supertag and Dependency Factored Model
复制标题
DOI：
10.18653/v1/p17-1026
复制
发表时间：
2017-04
期刊：
影响因子：
--
通讯作者：
Masashi Yoshikawa;Hiroshi Noji;Yuji Matsumoto
中科院分区：
文献类型：
--
作者：
Masashi Yoshikawa;Hiroshi Noji;Yuji Matsumoto
我们提出了一个新的A* CCG句法分析模型，在该模型中，一棵树的概率被分解成CCG类别的因素，其句法依赖关系都定义在双向LSTM。我们的因子模型允许预先计算所有概率并非常有效地运行，同时通过依赖关系显式地建模句子结构。我们的模型实现了国家的最先进的结果英语和日语的CCG解析。
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.