arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.05166cs.CLcs.AI
收藏

语法错误纠正:最先进技术的综述

Grammatical Error Correction: A Survey of the State of the Art

University of Cambridge(剑桥大学);Writer, Inc.(Writer公司);King’s College London(伦敦国王学院);National University of Singapore(新加坡国立大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

Christopher Bryant, Zheng Yuan, Muhammad Reza Qorib, Hannan Cao, Hwee Tou Ng, Ted Briscoe

AI总结:

本文综述了语法错误纠正领域的发展,涵盖语言挑战、数据集、方法(重点在人工错误生成)及评估可靠性问题,并展望未来方向,为研究者提供全面参考。

摘要:

语法错误纠正(GEC)是自动检测和纠正文本中错误的任务。该任务不仅包括语法错误的纠正,例如缺失介词和主谓不一致,还包括拼写错误和语义错误,例如拼写错误和用词选择错误。在过去十年中,该领域取得了显著进展,部分原因是五项共享任务的推动,这些任务推动了基于规则的方法、统计分类器、统计机器翻译以及最终代表当前主导最先进技术的神经机器翻译系统的发展。在这篇综述论文中,我们将该领域浓缩为一篇文章,首先概述该任务的一些语言挑战,介绍研究人员可用的最流行的数据集(适用于英语和其他语言),并总结已开发的各种方法和技术,特别关注人工错误生成。接下来,我们描述了许多不同的评估方法以及围绕度量可靠性的担忧,特别是与主观人类判断相关的问题,最后概述了近期进展并对未来工作和剩余挑战提出建议。我们希望这篇综述能为刚进入该领域或希望了解最新进展的研究人员提供全面的资源。

英文摘要:

Grammatical Error Correction (GEC) is the task of automatically detecting and correcting errors in text. The task not only includes the correction of grammatical errors, such as missing prepositions and mismatched subject-verb agreement, but also orthographic and semantic errors, such as misspellings and word choice errors respectively. The field has seen significant progress in the last decade, motivated in part by a series of five shared tasks, which drove the development of rule-based methods, statistical classifiers, statistical machine translation, and finally neural machine translation systems which represent the current dominant state of the art. In this survey paper, we condense the field into a single article and first outline some of the linguistic challenges of the task, introduce the most popular datasets that are available to researchers (for both English and other languages), and summarise the various methods and techniques that have been developed with a particular focus on artificial error generation. We next describe the many different approaches to evaluation as well as concerns surrounding metric reliability, especially in relation to subjective human judgements, before concluding with an overview of recent progress and suggestions for future work and remaining challenges. We hope that this survey will serve as comprehensive resource for researchers who are new to the field or who want to be kept apprised of recent developments.

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。

↑