Spell checker for consumer language (CSpell)
Spell checker for consumer language (CSpell)
复制标题
DOI：
10.1093/jamia/ocy171
复制
发表时间：
2019-03-01
影响因子：
6.4
通讯作者：
Demner-Fushman, Dina
中科院分区：
文献类型：
--
作者：
Lu, Chris J.;Aronson, Alan R.;Demner-Fushman, Dina
目的：消费者健康查询的自动化理解可能会受到拼写错误的阻碍。为了检测和纠正消费者健康问题中的各种类型的拼写错误，我们开发了一个分布式的拼写检查工具，CSpell，处理非字错误，真正的字错误，字边界违规，标点错误，以及上述的组合。方法：我们开发了一种新的方法，使用双嵌入Word 2 vec内的上下文相关的更正。该技术与基于词典的校正结合使用于2阶段排名系统中。我们还开发了各种分割器和处理程序来纠正单词边界违规。结果：我们的方法在拼写错误检测和纠正方面分别达到了80.93%和69.17%的F-1分数。讨论：双嵌入模型显示出显著的改进（9.13%）的F-1分数相比，使用余弦相似度与词向量在Word 2 vec的上下文排名的一般做法。我们的2阶段的排名系统显示了一个4.94%的F-1分数的改善相比，最好的1-stage ranking system.Conclusion：CSpell提高了最先进的国家，并提供近实时的自动拼写错误检测和纠正消费者的健康问题。该软件和CSpell测试集可在https://umlslex.nlm.nih.gov/cSpell上获得。
Objective: Automated understanding of consumer health inquiries might be hindered by misspellings. To detect and correct various types of spelling errors in consumer health questions, we developed a distributable spell-checking tool, CSpell, that handles nonword errors, real-word errors, word boundary infractions, punctuation errors, and combinations of the above.Methods: We developed a novel approach of using dual embedding within Word2vec for context-dependent corrections. This technique was used in combination with dictionary-based corrections in a 2-stage ranking system. We also developed various splitters and handlers to correct word boundary infractions. All correction approaches are integrated to handle errors in consumer health questions.Results: Our approach achieves an F-1 score of 80.93% and 69.17% for spelling error detection and correction, respectively.Discussion: The dual-embedding model shows a significant improvement (9.13%) in F-1 score compared with the general practice of using cosine similarity with word vectors in Word2vec for context ranking. Our 2-stage ranking system shows a 4.94% improvement in F-1 score compared with the best 1-stage ranking system.Conclusion: CSpell improves over the state of the art and provides near real-time automatic misspelling detection and correction in consumer health questions. The software and the CSpell test set are available at https://umlslex.nlm.nih.gov/cSpell.