哈萨克语句法分析辅助特征提取研究

在哈萨克语句法分析中,该文用平均感知器算法训练句法分析模型,用柱搜索算法进行解码,可以快速准确地对哈萨克语句子进行短语结构句法分析。在解析句子过程中,构建了一个双向LSTM模型,利用它提取句子中每个单词之间组成结构的信息,以预测每个单词在句法树中的句法组成部分,然后将结果作为辅助前瞻特征传递给句法分析过程。实验证明,此方法与基线模型相比,在准确率和召回率上均有提高。

Auxiliary Feature Extraction for Kazakh Syntactic Parsing

In the Kazakh syntax parsing, we use the averaged perceptron algorithm to train the syntactic parsing model, withthe beam search algorithm to decode the sentence structure. During the parsing, we construct a two-way LSTM model to extract the information between the structures of each word in the sentence to predict its syntactic role. Then we apply this information as a lookahead feature to the syntactic parsing process. Experiments show that this method has improved the precision and recall rate.