arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1611.08987cs.CL
收藏

利用未标记数据进行神经语法错误检测

Exploiting Unlabeled Data for Neural Grammatical Error Detection

Beihang University(北京航空航天大学);Tsinghua University(清华大学)

Zhuoran Liu, Yang Liu

摘要:

近年来,对非母语写作者语篇中语法错误的识别和纠正受到越来越多的关注。虽然已经建立了一些注释语料库,以促进数据驱动的语法错误检测和纠正方法,但它们在数量和覆盖范围方面仍然有限,因为人工注释是劳动密集型的,耗时的,昂贵的。在这项工作中,我们提出利用未标记的数据训练神经网络为基础的语法错误检测模型。其基本思想是将错误检测作为一个二元分类问题,并从未标记的数据中获得正面和负面的训练样本。我们引入了一个基于注意力的神经网络来捕获影响被检测单词的长距离依赖关系。实验表明,该方法的性能明显优于支持向量机和卷积网络与固定大小的上下文窗口。

英文摘要:

Identifying and correcting grammatical errors in the text written by non-native writers has received increasing attention in recent years. Although a number of annotated corpora have been established to facilitate data-driven grammatical error detection and correction approaches, they are still limited in terms of quantity and coverage because human annotation is labor-intensive, time-consuming, and expensive. In this work, we propose to utilize unlabeled data to train neural network based grammatical error detection models. The basic idea is to cast error detection as a binary classification problem and derive positive and negative training examples from unlabeled data. We introduce an attention-based neural network to capture long-distance dependencies that influence the word being detected. Experiments show that the proposed approach significantly outperforms SVMs and convolutional networks with fixed-size context window.

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。

↑