Effective Online Reordering with Arc-Eager Transitions
Effective Online Reordering with Arc-Eager Transitions
复制标题
DOI：
--
复制
发表时间：
2017-09
期刊：
影响因子：
--
通讯作者：
Ryosuke Kohita;Hiroshi Noji;Yuji Matsumoto
中科院分区：
文献类型：
--
作者：
Ryosuke Kohita;Hiroshi Noji;Yuji Matsumoto
我们提出了一个新的过渡系统与单词重排的非限制性非投射依赖分析。我们的系统是基于分解的弧渴望，而不是弧标准，它允许更灵活的本地投影和非本地交叉附件之间的歧义解决方案。在我们的实验中，我们发现我们的解析器优于普通的基于交换的解析器，特别是在具有大量非投射性的语言上。
We present a new transition system with word reordering for unrestricted non-projective dependency parsing. Our system is based on decomposed arc-eager rather than arc-standard, which allows more flexible ambiguity resolution between a local projective and non-local crossing attachment. In our experiment on Universal Dependencies 2.0, we find our parser outperforms the ordinary swap-based parser particularly on languages with a large amount of non-projectivity.