基于多层协同纠错的中文层次句法分析  

A Chinese Hierarchical Parsing Approach Based on Multi-layer Collaborative Correction

作　　者：蒋志鹏[1] 关毅[1] 董喜双[1] 

机构地区：[1]哈尔滨工业大学计算机科学与技术学院,黑龙江哈尔滨150001

出　　处：《中文信息学报》2014年第4期29-36,共8页Journal of Chinese Information Processing

基　　金：国家自然科学基金(60975077;90924015)

摘　　要：层次句法分析是一种简单快速的完全句法分析方法,该方法将句法分析分解为词性标注、组块分析和构建句法树三个阶段。该文将其中的组块分析细分为基本块分析和复杂块分析,利用条件随机域模型代替最大熵模型进行序列化标注。由于层次句分析中错误累积问题尤为严重,该文提出了一种简单可行的错误预判及协同纠错算法,跟踪本层预判的错误标注结果进入下一层,利用两层预测分数相结合的方式协同纠错。实验结果表明,加入纠错方法后,层次句法分析在保证解析速度的同时,获得了与主流中文句法分析器相当的解析精度。Hierarchical parsing is a simple and rapid complete syntactic analysis method, which can be decomposed into three stages： POS tagging, chunking and parsing tree construction. In this paper, chunking is further divided into base chunking and complex chunking, and conditional random field model is adopted for sequence labeling in- stead of maximum entropy model. Considering error accumulation, which is a particularly serious problem in hierarchical parsing, this paper presents a simple and practical error predicting and collaborative correcting method, by tracking the predicted errors in this layer to the next layer and combines prediction scores of two layers to correct error collaboratively. The experimental results show that hierarchical parsing with error correction achieves almost the same analytic precision of the mainstream prediction Chinese parsers.

关 键 词：层次句法分析 条件随机域模型 组块分析 多层协同纠错 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]