Recovering Non-Local Dependencies for Chinese
Recovering Non-Local Dependencies for Chinese
复制标题
DOI：
--
复制
发表时间：
2007-06
期刊：
影响因子：
--
通讯作者：
Yuqing Guo;Haifeng Wang;Josef van Genabith
中科院分区：
文献类型：
--
作者：
Yuqing Guo;Haifeng Wang;Josef van Genabith
到目前为止，非本地学习（NLDs）的工作几乎完全集中在英语上，这些方法如何迁移到其他语言是一个开放的研究问题。本文考察了Penn汉语树库（CTB）中的非局部依存结构，并提出了一种从表层上下文无关短语结构树中生成包含非局部依存结构的谓词-论元-修饰语结构的方法。我们的方法恢复非本地的依赖关系在词汇功能语法的f-结构的水平，使用自动获取的子分类框架和f-结构路径连接的先行词和痕迹在NLD。目前，我们的算法实现了92.2%的跟踪插入和84.3%的先行恢复评价的黄金标准CTB树，和64.7%和54.7%，分别在CTB训练的最先进的解析器输出树。
To date, work on Non-Local Dependencies (NLDs) has focused almost exclusively on English and it is an open research question how well these approaches migrate to other languages. This paper surveys non-local dependency constructions in Chinese as represented in the Penn Chinese Treebank (CTB) and provides an approach for generating proper predicate-argument-modifier structures including NLDs from surface contextfree phrase structure trees. Our approach recovers non-local dependencies at the level of Lexical-Functional Grammar f-structures, using automatically acquired subcategorisation frames and f-structure paths linking antecedents and traces in NLDs. Currently our algorithm achieves 92.2% f-score for trace insertion and 84.3% for antecedent recovery evaluating on gold-standard CTB trees, and 64.7% and 54.7%, respectively, on CTBtrained state-of-the-art parser output trees.