arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.04443cs.CL
收藏

基于多假设的语法纠错神经质量估计

Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction

Tsinghua University(清华大学);Beijing National Research Center for Information Science and Technology(北京信息科学与技术国家研究中心);Beijing Academy of Artificial Intelligence(北京人工智能研究院);Beijing Language and Culture University(北京语言大学);National University of Singapore(新加坡国立大学)

Zhenghao Liu, Xiaoyuan Yi, Maosong Sun, Liner Yang, Tat-Seng Chua

摘要:

语法错误纠正(GEC)旨在纠正写作错误并帮助语言学习者提高写作技巧。然而,现有的GEC模型往往会产生虚假的校正或无法检测到大量的错误。质量评估模型是必要的,以确保学习者得到准确的GEC结果,并避免误导错误的句子。经过良好训练的GEC模型可以通过解码(如束搜索)生成多个高质量的假设,这些假设提供了有价值的GEC证据,可以用于评估GEC质量。然而,现有的模型忽略了可能的GEC证据,从不同的假设。本文提出了一种用于多假设GEC质量估计的神经验证网络(VERNet)。VERNet通过推理图建立假设之间的交互关系,并通过两种注意力机制传播GEC证据,验证生成假设的质量。我们在四个GEC数据集上的实验表明,VERNet实现了最先进的语法错误检测性能,实现了最佳的质量估计结果,并通过重新排序假设显着提高了GEC性能。所有数据和源代码都可以在www.example.com上找到。

英文摘要:

Grammatical Error Correction (GEC) aims to correct writing errors and help language learners improve their writing skills. However, existing GEC models tend to produce spurious corrections or fail to detect lots of errors. The quality estimation model is necessary to ensure learners get accurate GEC results and avoid misleading from poorly corrected sentences. Well-trained GEC models can generate several high-quality hypotheses through decoding, such as beam search, which provide valuable GEC evidence and can be used to evaluate GEC quality. However, existing models neglect the possible GEC evidence from different hypotheses. This paper presents the Neural Verification Network (VERNet) for GEC quality estimation with multiple hypotheses. VERNet establishes interactions among hypotheses with a reasoning graph and conducts two kinds of attention mechanisms to propagate GEC evidence to verify the quality of generated hypotheses. Our experiments on four GEC datasets show that VERNet achieves state-of-the-art grammatical error detection performance, achieves the best quality estimation results, and significantly improves GEC performance by reranking hypotheses. All data and source codes are available at https://github.com/thunlp/VERNet.

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。

↑