English Multiword Expression-aware Dependency Parsing Including Named Entities
English Multiword Expression-aware Dependency Parsing Including Named Entities
复制标题
DOI：
10.18653/v1/p17-2068
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
Akihiko Kato;Hiroyuki Shindo;Yuji Matsumoto
中科院分区：
文献类型：
--
作者：
Akihiko Kato;Hiroyuki Shindo;Yuji Matsumoto
由于在许多英语句法语料库中，多词表达式的句法结构和句法跨度都是独立标注的，它们之间通常是不一致的，这不利于聚合系统的实现。在这项工作中，我们构建了一个语料库，以确保依赖结构和MWEs（包括命名实体）之间的一致性。此外，我们探索了预测mwe跨度和mwe感知依赖结构的模型。实验结果表明，使用附加的MWE-span特征的联合模型比管道模型的MWE识别率提高了1.35分。
Because syntactic structures and spans of multiword expressions (MWEs) are independently annotated in many English syntactic corpora, they are generally inconsistent with respect to one another, which is harmful to the implementation of an aggregate system. In this work, we construct a corpus that ensures consistency between dependency structures and MWEs, including named entities. Further, we explore models that predict both MWE-spans and an MWE-aware dependency structure. Experimental results show that our joint model using additional MWE-span features achieves an MWE recognition improvement of 1.35 points over a pipeline model.