Improved Character-Based Chinese Dependency Parsing by Using Stack-Tree LSTM

摘要：

　　Almost all the state-of-the-art methods for Character-based Chinese dependency parsing ignore the complete dependency subtree information built during the parsing process,which is crucial for parsing the rest part of the sentence.In this paper,we introduce a novel neural network architecture to capture dependency subtree feature.We extend and improve recent works in neural joint model for Chinese word segmentation,POS tagging and dependency parsing,and adopt bidirectional LSTM to learn n-gram feature representation and context information.The neural network and bidirectional LSTMs are trained jointly with the parser objective,resulting in very effective feature extractors for parsing.Finally,we conduct experiments on Penn Chinese Treebank 5,and demonstrate the effectiveness of the approach by applying it to a greedy transition-based parser.The results show that our model outperforms the state-of-the-art neural joint models in Chinese word segmentation,POS tagging and dependency parsing.

关键词： Chinese word segmentation POS tagging and dependency parsing Dependency subtree Neural network architecture

作者: Hang Liu Mingtong Liu Yujie Zhang Jinan Xu Yufeng Chen

作者单位: School of Computer and Information Technology,Beijing Jiaotong University,Beijing,China

会议类型: 国际会议

会议名称: 2018自然语言处理与中文计算国际会议(NLPCC2018)

会议地点: 呼和浩特

会议语种:英文

页码: 203-212

在线出版日期: 2018-08-26（万方平台首次上网日期，不代表论文的发表时间）