arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.12409cs.CL
收藏

基于元学习的Few-Shot领域自适应语法纠错

Few-Shot Domain Adaptation for Grammatical Error Correction via Meta-Learning

Beijing Jiaotong University(北京交通大学);Beijing Language and Culture University(北京语言大学);Shanghai University of Finance and Economics(上海财经大学);Beijing University of Technology(北京工业大学)

Shengsheng Zhang, Yaping Huang, Yun Chen, Liner Yang, Chencheng Wang, Erhong Yang

摘要:

现有的基于序列对序列的语法纠错方法主要关注如何产生更多的伪数据以获得更好的性能。很少有工作涉及Few-Shot GEC领域自适应。在本文中,我们把不同的GEC领域不同的GEC任务,并提出了扩展元学习Few-Shot GEC领域自适应,而不使用任何伪数据。我们利用一组数据丰富的源域来学习模型参数的初始化,以便于快速适应新的资源贫乏的目标域。我们将GEC模型应用于第二语言学习者的第一语言(L1)。为了评估所提出的方法,我们使用9个L1作为源域和5个L1作为目标域。在L1 GEC领域自适应数据集上的实验结果表明,该方法比多任务迁移学习基线的平均$F_{0.5}$得分高出0.50,并使我们能够有效地适应一个只有200个平行句子的新L1领域。

英文摘要:

Most existing Grammatical Error Correction (GEC) methods based on sequence-to-sequence mainly focus on how to generate more pseudo data to obtain better performance. Few work addresses few-shot GEC domain adaptation. In this paper, we treat different GEC domains as different GEC tasks and propose to extend meta-learning to few-shot GEC domain adaptation without using any pseudo data. We exploit a set of data-rich source domains to learn the initialization of model parameters that facilitates fast adaptation on new resource-poor target domains. We adapt GEC model to the first language (L1) of the second language learner. To evaluate the proposed method, we use nine L1s as source domains and five L1s as target domains. Experiment results on the L1 GEC domain adaptation dataset demonstrate that the proposed approach outperforms the multi-task transfer learning baseline by 0.50 $F_{0.5}$ score on average and enables us to effectively adapt to a new L1 domain with only 200 parallel sentences.

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。

↑