arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.09609cs.CL
收藏

基于神经迁移的句法线性化

Neural Transition-based Syntactic Linearization

University of Rochester(罗切斯特大学);Westlake University(西湖大学)

Linfeng Song, Yue Zhang, Daniel Gildea

摘要:

线性化的任务是找到给定一组单词的语法顺序。传统模型使用统计方法。句法线性化系统,生成一个句子及其句法树,已经显示出最先进的性能。最近的工作表明,多层LSTM语言模型在不使用语法的情况下优于竞争性统计语法线性化系统。在本文中,我们研究了神经语法线性化,利用前馈神经网络构建了一个基于转换的语法线性化器,与LSTM语言模型相比,在这项任务上观察到了更好的结果。

英文摘要:

The task of linearization is to find a grammatical order given a set of words. Traditional models use statistical methods. Syntactic linearization systems, which generate a sentence along with its syntactic tree, have shown state-of-the-art performance. Recent work shows that a multi-layer LSTM language model outperforms competitive statistical syntactic linearization systems without using syntax. In this paper, we study neural syntactic linearization, building a transition-based syntactic linearizer leveraging a feed-forward neural network, observing significantly better results compared to LSTM language models on this task.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑