arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.06600cs.CLcs.LG
收藏

语法纠错综述

A Comprehensive Survey of Grammar Error Correction

College of Artificial Intelligence, Nankai University(南开大学人工智能学院)

Yu Wang, Yuelin Wang, Jie Liu, Zhuo Liu

摘要:

语法纠错是自然语言处理技术的一个重要应用领域。在过去的十年中,由于机器学习和深度学习的日益普及,GEC取得了重大进展,特别是在2010年代后期,接近人类水平的GEC系统可用。然而,没有先前的工作集中在整个概括的进展。我们提出的第一次调查,在GEC在这方面的文献进行了全面回顾。首先介绍了五个公共数据集、数据标注模式、两个重要的共享任务和四个标准的评价指标。更重要的是,我们讨论了四种基本方法,包括基于统计的机器翻译方法,基于神经机器翻译方法,基于分类的方法和基于语言模型的方法,六种常用的GEC系统的性能提升技术和两种数据增强方法。由于GEC通常被视为机器翻译的姊妹任务,因此许多GEC系统基于神经机器翻译(NMT)方法,其中应用神经序列到序列模型。类似地,一些性能提升技术改编自机器翻译,并成功地与GEC系统相结合,以提高最终的性能。在此基础上,分别从基本方法、性能提升技术和集成GEC系统三个层面对它们的实验结果进行了分析,得到了更清晰的模式和结论。最后,我们讨论了未来GEC研究的五个前景方向。

英文摘要:

Grammar error correction (GEC) is an important application aspect of natural language processing techniques. The past decade has witnessed significant progress achieved in GEC for the sake of increasing popularity of machine learning and deep learning, especially in late 2010s when near human-level GEC systems are available. However, there is no prior work focusing on the whole recapitulation of the progress. We present the first survey in GEC for a comprehensive retrospect of the literature in this area. We first give the introduction of five public datasets, data annotation schema, two important shared tasks and four standard evaluation metrics. More importantly, we discuss four kinds of basic approaches, including statistical machine translation based approach, neural machine translation based approach, classification based approach and language model based approach, six commonly applied performance boosting techniques for GEC systems and two data augmentation methods. Since GEC is typically viewed as a sister task of machine translation, many GEC systems are based on neural machine translation (NMT) approaches, where the neural sequence-to-sequence model is applied. Similarly, some performance boosting techniques are adapted from machine translation and are successfully combined with GEC systems for enhancement on the final performance. Furthermore, we conduct an analysis in level of basic approaches, performance boosting techniques and integrated GEC systems based on their experiment results respectively for more clear patterns and conclusions. Finally, we discuss five prospective directions for future GEC researches.

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。

↑