基于RNN的中文二分结构句法分析

为了构建一个简单易扩展的中文句法分析器,我们依据朱德熙和陆俭明先生的中文二分结构的层次分析句法理论,手工构建了一个3万句的二分结构的中文句法树库,并使用哈夫曼编码方式来简化表示完全二叉树的层次结构。该文将中文句法分析转换为迭代二分的序列标注问题,并根据该任务的特点,提出了在词的间隔上进行标记的序列标注模型(RNN-Interval,RNN-INT),与常用的循环神经网络模型(RNN,LSTM)和条件随机场模型(CRF)进行对比实验,使用mx2交叉验证序贯t-检验来比较模型。实验结果表明,RNN-INT模型在窗口为1的词特征就可达到最好的性能,并好于其他窗口大小和其他序列标注模型(RNN,LSTM,CRF)。最后,在测试集上,在人工分词下,RNN-INT在短语级别的F₁值(块F₁) 达到71.25%,在句子级别的准确率达到约43%。

RNN Based Chinese Parsing for Binary Tree Structure

We construct a 30 000 sentences binary Chinese Treebank which is base on Chinese syntactic theory proposed by Zhu DeXi and Lu JianMin, in which each parse is a full binary tree and represented by Huffman coding for simplicity. To deal with its parsing, we propose a sequential labeling model (RNN-Interval, abbr RNN-INT) based on RNN(recurrent neural network) tagging the intervals between words. We compared our model RNN-INT with primary RNN, LSTM and CRF models, employing the m×2 cross-validated sequential t-test. The experiment results show that the proposed model achieves the best performance with window size 1according to constituency F₁ and sentence accuracy, i.e. 71.25% and 43%, respectively.