从机器翻译与原语言随机试验报告中提取数据：一项比较研究。
Data extraction from machine-translated versus original language randomized trial reports: a comparative study.
作者信息
Balk Ethan M, Chung Mei, Chen Minghua L, Chang Lina Kong Win, Trikalinos Thomas A
机构信息
Tufts Evidence-based Practice Center, Institute for Clinical Research and Health Policy Studies, 800 Washington Street, Box 63, Boston, MA 02111, USA.
出版信息
Syst Rev. 2013 Nov 7;2:97. doi: 10.1186/2046-4053-2-97.
BACKGROUND
Google Translate offers free Web-based translation, but it is unknown whether its translation accuracy is sufficient to use in systematic reviews to mitigate concerns about language bias.
METHODS
We compared data extraction from non-English language studies with extraction from translations by Google Translate of 10 studies in each of five languages (Chinese, French, German, Japanese and Spanish). Fluent speakers double-extracted original-language articles. Researchers who did not speak the given language double-extracted translated articles along with 10 additional English language trials. Using the original language extractions as a gold standard, we estimated the probability and odds ratio of correctly extracting items from translated articles compared with English, adjusting for reviewer and language.
RESULTS
Translation required about 30 minutes per article and extraction of translated articles required additional extraction time. The likelihood of correct extractions was greater for study design and intervention domain items than for outcome descriptions and, particularly, study results. Translated Spanish articles yielded the highest percentage of items (93%) that were correctly extracted more than half the time (followed by German and Japanese 89%, French 85%, and Chinese 78%) but Chinese articles yielded the highest percentage of items (41%) that were correctly extracted >98% of the time (followed by Spanish 30%, French 26%, German 22%, and Japanese 19%). In general, extractors' confidence in translations was not associated with their accuracy.
CONCLUSIONS
Translation by Google Translate generally required few resources. Based on our analysis of translations from five languages, using machine translation has the potential to reduce language bias in systematic reviews; however, pending additional empirical data, reviewers should be cautious about using translated data. There remains a trade-off between completeness of systematic reviews (including all available studies) and risk of error (due to poor translation).
背景
谷歌翻译提供基于网络的免费翻译服务，但尚不清楚其翻译准确性是否足以用于系统评价，以减轻对语言偏倚的担忧。
方法
我们将非英语研究的数据提取与谷歌翻译对五种语言（中文、法语、德语、日语和西班牙语）中每项10项研究的翻译提取进行了比较。精通相应语言的人员对原文进行了双重提取。不懂相应语言的研究人员对翻译后的文章以及另外10篇英语试验进行了双重提取。以原文提取作为金标准，我们估计了与英语相比，从翻译文章中正确提取项目的概率和优势比，并对审阅者和语言进行了调整。
结果
每篇文章的翻译大约需要30分钟，翻译文章的提取需要额外的提取时间。研究设计和干预领域项目正确提取的可能性大于结果描述，尤其是研究结果。翻译后的西班牙语文章中，超过一半的时间正确提取的项目比例最高（93%，其次是德语和日语89%，法语85%，中文78%），但中文文章中98%以上时间正确提取的项目比例最高（41%，其次是西班牙语30%，法语26%，德语22%，日语19%）。一般来说，提取者对翻译的信心与翻译准确性无关。
结论
谷歌翻译通常所需资源较少。基于我们对五种语言翻译的分析，使用机器翻译有可能减少系统评价中的语言偏倚；然而，在有更多实证数据之前，审阅者在使用翻译数据时应谨慎。在系统评价的完整性（包括所有可用研究）和错误风险（由于翻译不佳）之间仍然存在权衡。
Zotero 插件