ClearTAC: Verb Tense, Aspect, and Form Classification Using Neural Nets

ClearTAC: Verb Tense, Aspect, and Form Classification Using Neural Nets
复制标题

DOI：
10.18653/v1/w19-3315
复制
发表时间：
2019
期刊：
Proceedings of the First International Workshop on Designing Meaning Representations
影响因子：
--
通讯作者：
Skatje Myers;Martha Palmer
Skatje Myers;Martha Palmer
中科院分区：
其他
文献类型：
--
作者：
Skatje Myers;Martha Palmer

文献摘要

相似文献

本文提出使用双向LSTM-CRF模型来识别动词的时体。该分类器输出的信息对于对事件进行排序可能是有用的，并且可以提供预处理步骤以提高注释这种类型的信息的效率。这种神经网络架构已成功用于其他顺序标记任务，我们表明，它显着优于基于规则的工具TMV注释器的Propbank I数据集。
This paper proposes using a Bidirectional LSTM-CRF model in order to identify the tense and aspect of verbs. The information that this classifier outputs can be useful for ordering events and can provide a pre-processing step to improve efficiency of annotating this type of information. This neural network architecture has been successfully employed for other sequential labeling tasks, and we show that it significantly outperforms the rule-based tool TMV-annotator on the Propbank I dataset.