arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.07421cs.CLcs.LG
收藏

基于软屏蔽BERT的拼写错误纠正

Spelling Error Correction with Soft-Masked BERT

ByteDance AI Lab(字节跳动人工智能实验室);Fudan University(复旦大学)

Shaohua Zhang, Haoran Huang, Jicong Liu, Hang Li

摘要:

拼写纠错是一项重要而又具有挑战性的任务,因为要圆满地解决拼写错误,需要具备人类水平的语言理解能力。在不失一般性的前提下,本文研究了汉语拼写纠错问题。用于该任务的最先进的方法基于语言表示模型BERT从候选列表中选择用于在句子的每个位置处进行校正(包括不校正)的字符。然而,该方法的准确性可能是次优的,因为BERT不具有足够的能力来检测每个位置处是否存在错误,这显然是由于使用掩码语言建模对其进行预训练的方式。在这项工作中,我们提出了一种新的神经架构,以解决上述问题,其中包括一个网络的错误检测和错误校正的基础上BERT的网络,与前者被连接到后者,我们称之为软屏蔽技术。我们使用“软屏蔽BERT”的方法是通用的,它可以用于其他语言检测校正问题。在两个数据集上的实验结果表明,我们提出的方法的性能显着优于基线,包括一个单独的基础上BERT。

英文摘要:

Spelling error correction is an important yet challenging task because a satisfactory solution of it essentially needs human-level language understanding ability. Without loss of generality we consider Chinese spelling error correction (CSC) in this paper. A state-of-the-art method for the task selects a character from a list of candidates for correction (including non-correction) at each position of the sentence on the basis of BERT, the language representation model. The accuracy of the method can be sub-optimal, however, because BERT does not have sufficient capability to detect whether there is an error at each position, apparently due to the way of pre-training it using mask language modeling. In this work, we propose a novel neural architecture to address the aforementioned issue, which consists of a network for error detection and a network for error correction based on BERT, with the former being connected to the latter with what we call soft-masking technique. Our method of using `Soft-Masked BERT' is general, and it may be employed in other language detection-correction problems. Experimental results on two datasets demonstrate that the performance of our proposed method is significantly better than the baselines including the one solely based on BERT.

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。

↑