Parseme Shared Task on Automatic Identification of VMWEs:Neural Multiword Expression Tagging with High Generalisation
SHOMA at Parseme Shared Task on Automatic Identification of VMWEs: Neural Multiword Expression Tagging with High Generalisation
摘要:
本文提出了一种与语言无关的深度学习架构,适用于多词表达式(MWE)识别任务。我们采用了一种神经架构,包括卷积层和递归层,并在顶部添加了一个可选的CRF层。由于使用了预训练的维基百科词嵌入,该系统参与了关于自动识别口头MWE的Parseme共享任务的开放跟踪。它在开放和封闭赛道上的表现都优于所有参与系统,所有语言的总体宏观平均MWE F1得分为58.09。该系统的一个特殊优势是其对不可见数据录入的卓越性能。
英文摘要:
This paper presents a language-independent deep learning architecture adapted to the task of multiword expression (MWE) identification. We employ a neural architecture comprising of convolutional and recurrent layers with the addition of an optional CRF layer at the top. This system participated in the open track of the Parseme shared task on automatic identification of verbal MWEs due to the use of pre-trained wikipedia word embeddings. It outperformed all participating systems in both open and closed tracks with the overall macro-average MWE-based F1 score of 58.09 averaged among all languages. A particular strength of the system is its superior performance on unseen data entries.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。