RuGECToR: Rule-Based Neural Network Model for Russian Language Grammatical Error Correction

IF 0.7 4区计算机科学 Q4 COMPUTER SCIENCE, SOFTWARE ENGINEERING Programming and Computer Software Pub Date : 2024-07-30 DOI:10.1134/s0361768824700129

I. A. Khabutdinov, A. V. Chashchin, A. V. Grabovoy, A. S. Kildyakov, U. V. Chekhovich

{"title":"RuGECToR: Rule-Based Neural Network Model for Russian Language Grammatical Error Correction","authors":"I. A. Khabutdinov, A. V. Chashchin, A. V. Grabovoy, A. S. Kildyakov, U. V. Chekhovich","doi":"10.1134/s0361768824700129","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>Grammatical error correction is one of the core natural language processing tasks. Presently, the open-source state-of-the-art sequence tagging for English is the GECToR model. For Russian, this problem does not have equally effective solutions due to the lack of annotated datasets, which motivated the current research. In this paper, we describe the process of creating a synthetic dataset and training the model on it. The GECToR architecture is adapted for the Russian language, and it is called RuGECToR. This architecture is chosen because, unlike the sequence-to-sequence approach, it is easy to interpret and does not require a lot of training data. The aim is to train the model in such a way that it generalizes the morphological properties of the language rather than adapts to a specific training sample. The presented model achieves the quality of <b>82.5</b> in the metric <span>\\({{{\\mathbf{F}}}_{{{\\mathbf{0}}{\\mathbf{.5}}}}}\\)</span> on synthetic data and <b>22.2</b> on the RULEC dataset, which was not used at the training stage.</p>","PeriodicalId":54555,"journal":{"name":"Programming and Computer Software","volume":null,"pages":null},"PeriodicalIF":0.7000,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Programming and Computer Software","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1134/s0361768824700129","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}

引用次数: 0

Abstract

Grammatical error correction is one of the core natural language processing tasks. Presently, the open-source state-of-the-art sequence tagging for English is the GECToR model. For Russian, this problem does not have equally effective solutions due to the lack of annotated datasets, which motivated the current research. In this paper, we describe the process of creating a synthetic dataset and training the model on it. The GECToR architecture is adapted for the Russian language, and it is called RuGECToR. This architecture is chosen because, unlike the sequence-to-sequence approach, it is easy to interpret and does not require a lot of training data. The aim is to train the model in such a way that it generalizes the morphological properties of the language rather than adapts to a specific training sample. The presented model achieves the quality of 82.5 in the metric \({{{\mathbf{F}}}_{{{\mathbf{0}}{\mathbf{.5}}}}}\) on synthetic data and 22.2 on the RULEC dataset, which was not used at the training stage.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

RuGECToR：基于规则的俄语语法纠错神经网络模型

摘要语法纠错是自然语言处理的核心任务之一。目前，GECToR 模型是最先进的开源英语语序标记模型。对于俄语而言，由于缺乏注释数据集，这一问题并没有同样有效的解决方案，这也是当前研究的动机所在。在本文中，我们描述了创建合成数据集并在其上训练模型的过程。GECToR 架构适用于俄语，被称为 RuGECToR。之所以选择这种架构，是因为它不同于序列到序列的方法，易于解释，而且不需要大量的训练数据。其目的是以这样一种方式来训练模型，使其概括语言的形态属性，而不是适应特定的训练样本。所提出的模型在合成数据上的质量指标（{{\mathbf{F}}}_{{{\mathbf{0}}{{mathbf{.5}}}}}）达到了 82.5，在 RULEC 数据集上的质量指标（训练阶段没有使用该数据集）达到了 22.2。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Programming and Computer Software 工程技术-计算机：软件工程

CiteScore

1.60

自引率

28.60%

发文量

审稿时长

>12 weeks

期刊介绍： Programming and Computer Software is a peer reviewed journal devoted to problems in all areas of computer science: operating systems, compiler technology, software engineering, artificial intelligence, etc.