融合丰富语言知识的汉语统计句法分析

Chinese Statistical Parsing with Rich Linguistic Features

知识获取一直以来是自然语言处理中的瓶颈,基于树库的统计句法分析也不例外。树库中潜在隐含的语言知识是非常丰富的,但它们并不是可以直接得到,往往需要特定的策略才能将它们融合到模型中。我们的汉语统计句法分析模型从3个方面融合潜在的丰富语言知识:1)重新标注树库中的非递归名词短语和非递归动词短语;2 )设计新的中心词映射表;3)引进上下文配置框架以更具体地描述二元依存结构。由于融合了以上三种潜在语言知识,模型的F1值提高了2 37% ,完全匹配正确率提高了5 36 %。

Knowledge acquisition is always regarded as a bottleneck in many NLP tasks, such as machine translation, information extraction. Treebank-based statistical parsing is not an exceptant. The latent linguistic knowledge in treebank is very rich, which, however, cant be acquired directly.In our model, the following three ways are used to incorporate such rich linguistic features for Chinese statistical parsing. First of all, non-recursive noun and verb phrases are annotated in the Penn Chinese Treebank because of their strong mark of boundaries. Second, a new head percolation table is designed based on Xias table. The last linguistic feature our model uses is the context configuration frame which provides a stronger representation of bilexical dependency structures. All these three linguistic features gain an improvement of remarkable 2.37% in terms of F1 measure, 5.36% in terms of complete match ratio.