arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.06407cs.CLcs.AI
收藏

纠正真实单词拼写错误:一种新的混合方法

Correcting Real-Word Spelling Errors: A New Hybrid Approach

Seyed MohammadSadegh Dashti, Amid Khatibi Bardsiri, Vahid Khatibi Bardsiri

摘要:

拼写纠正是自然语言处理领域的主要任务之一。与常见的拼写错误相反,传统的拼写校正方法无法检测到真实单词错误。Mays、Damerau和Mercer提出的实词纠错模型在不同的评价中表现出很好的性能。然而,在这项研究中,提出了一种新的混合方法,它依赖于统计和句法知识来检测和纠正实词错误。在这个模型中,约束语法(CG)被用来区分在搜索空间中的校正候选集。Mays,Damerau和Mercer的三元组方法被操纵来估计句法上良好形式的校正候选者的概率。这里提出的方法是测试华尔街日报语料库。该模型比Hirst和Budanitsky提出的基于WordNet的方法和Wilcox-O 'Hearn和Hirst提出的固定窗口大小的方法更实用。

英文摘要:

Spelling correction is one of the main tasks in the field of Natural Language Processing. Contrary to common spelling errors, real-word errors cannot be detected by conventional spelling correction methods. The real-word correction model proposed by Mays, Damerau and Mercer showed a great performance in different evaluations. In this research, however, a new hybrid approach is proposed which relies on statistical and syntactic knowledge to detect and correct real-word errors. In this model, Constraint Grammar (CG) is used to discriminate among sets of correction candidates in the search space. Mays, Damerau and Mercer's trigram approach is manipulated to estimate the probability of syntactically well-formed correction candidates. The approach proposed here is tested on the Wall Street Journal corpus. The model can prove to be more practical than some other models, such as WordNet-based method of Hirst and Budanitsky and fixed windows size method of Wilcox-O'Hearn and Hirst.

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。

↑