Enhancing Shift-Reduce Constituent Parsing with Action N-Gram Model
Hao Zhou, Shujian Huang, Junsheng Zhou, Yue Zhang, Huadong Chen, Xinyu Dai, Chuan Cheng, Jiajun Chen · ACM Transactions on Asian and Low-Resource Language Information Processing · 2016
Current shift-reduce parsers “understand” the context by embodying a large number of binary indicator features with a discriminative model. In this article, we propose the action n-gram model, which utilizes the action sequence to help parsing disambiguation. The action n-gram model is trained on action sequences produced by parsers with the n-gram estimation method, which gives a smoothed maximum likelihood estimation of the action probability given a specific action history. We show that incorporating action n-gram models into a state-of-the-art parsing framework could achieve parsing accuracy improvements on three datasets across two languages.