Deep Neural Networks for Syntactic Parsing of Morphologically Rich Languages
Deep Neural Networks for Syntactic Parsing of Morphologically Rich Languages
复制标题
DOI：
10.18653/v1/p16-2093
复制
发表时间：
2016-08
影响因子：
7
通讯作者：
Joël Legrand;R. Collobert
中科院分区：
文献类型：
--
作者：
Joël Legrand;R. Collobert
形态丰富的语言(MRL)是一种语言，其中的大部分结构信息包含在单词层面上，导致了高水平的词形变化。在历史上，句法分析主要是使用生成模型来处理的。这些模型假定输入特征是有条件的独立的，这使得很难结合任意特征。在这篇文章中，我们研究了(Legrand and Collobert，2015)中描述的基于词嵌入的贪婪判别式句法分析器。我们建议学习形态嵌入，并使用递归合成过程在树中传播形态信息。实验表明，这种嵌入方式可以显著提高不同语言的平均性能。此外，它为大多数语言提供了最先进的性能。
Morphologically rich languages (MRL) are languages in which much of the structural information is contained at the wordlevel, leading to high level word-form variation. Historically, syntactic parsing has been mainly tackled using generative models. These models assume input features to be conditionally independent, making difficult to incorporate arbitrary features. In this paper, we investigate the greedy discriminative parser described in (Legrand and Collobert, 2015), which relies on word embeddings, in the context of MRL. We propose to learn morphological embeddings and propagate morphological information through the tree using a recursive composition procedure. Experiments show that such embeddings can dramatically improve the average performance on different languages. Moreover, it yields state-of-the art performance for a majority of languages.