Neural Generative Rhetorical Structure Parsing-猫眼课题宝

DOI：

10.18653/v1/d19-1233

发表时间：

2019-09

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Amandla Mabona;Laura Rimell;S. Clark;Andreas Vlachos

修辞结构树已被证明是有用的几个文档级的任务，包括摘要和文档分类。以前的方法来解析数据集使用判别模型;然而，这些模型比生成模型的样本效率低，并且解析数据集通常很小。在本文中，我们提出了第一个生成式模型的句法分析。我们的模型是一个文档级的RNN语法（RNNG），具有自底向上的遍历顺序。我们表明，对于我们的解析器的遍历顺序，之前的RNNG束搜索算法具有左分支偏差，这不适合RST解析。我们开发了一种新型的束搜索算法，可以跟踪结构和单词生成操作，而不会表现出这种分支偏差，并且与之前的算法相比，未标记和标记的F1的绝对改进分别为6.8和2.9。总的来说，我们的生成模型比具有相同特征的判别模型高出2.6个F1点，并且达到了与最先进的性能相当的性能，超过了最近一项不使用额外训练数据的复制研究中所有已发表的解析器

Rhetorical structure trees have been shown to be useful for several document-level tasks including summarization and document classification. Previous approaches to RST parsing have used discriminative models; however, these are less sample efficient than generative models, and RST parsing datasets are typically small. In this paper, we present the first generative model for RST parsing. Our model is a document-level RNN grammar (RNNG) with a bottom-up traversal order. We show that, for our parser’s traversal order, previous beam search algorithms for RNNGs have a left-branching bias which is ill-suited for RST parsing.We develop a novel beam search algorithm that keeps track of both structure-and word-generating actions without exhibit-ing this branching bias and results in absolute improvements of 6.8 and 2.9 on unlabelled and labelled F1 over previous algorithms. Overall, our generative model outperforms a discriminative model with the same features by 2.6 F1points and achieves performance comparable to the state-of-the-art, outperforming all published parsers from a recent replication study that do not use additional training data

Neural Generative Rhetorical Structure Parsing

文献摘要

被引文献

相似文献