A Dynamic Window Neural Network for CCG Supertagging

	A Dynamic Window Neural Network for CCG Supertagging
	Wu HJ(吴惠甲); Zhang JJ(张家俊); Zong CQ(宗成庆); Zong CQ(宗成庆)
	2017-02
会议名称	AAAI-17
会议日期	2017
会议地点	美国
摘要	Combinatory Category Grammar (CCG) supertagging is a task to assign lexical categories to each word in a sentence. Almost all previous methods use fixed context window sizes as input features. However, it is obvious that different tags usually rely on different context window sizes. These motivate us to build a supertagger with a dynamic window approach, which can be treated as an attention mechanism on the local contexts. Applying dropout on the dynamic filters can be seen as drop on words directly, which is superior to the regular dropout on word embeddings. We use this approach to demonstrate the state-of-the-art CCG supertagging performance on the standard test set.
关键词	Supertagging Dynamic Window Attention Mechanism
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/41027
专题	多模态人工智能系统全国重点实验室_自然语言处理
通讯作者	Zong CQ(宗成庆)
推荐引用方式 GB/T 7714	Wu HJ,Zhang JJ,Zong CQ,et al. A Dynamic Window Neural Network for CCG Supertagging[C],2017.