利用机器翻译增强多语言分类
Using Machine Translation to Augment Multilingual Classification
AI总结：
本文研究利用机器翻译生成跨语言标注数据以微调多语言分类器，并引入源自图像字幕领域的损失技术缓解翻译数据负面影响，实验证明其可带来性能提升。
摘要：
文本分类模型开发中一个普遍存在的瓶颈是需要标注训练数据，而对于多语言分类器而言，这一需求成倍增加。幸运的是，当代机器翻译模型既易于获取，又具备可靠的翻译质量，使将标注训练数据从一种语言翻译成另一种语言成为可能。本文探索利用机器翻译来微调多语言模型，以完成跨多种语言的分类任务，并研究采用一种最初在图像字幕领域提出的新技术所带来的收益，该技术用于应对在翻译数据上微调模型可能产生的负面影响。研究表明，翻译数据具有足够高的质量，可用于微调多语言分类器，并且这种新颖的损失函数技术相较未使用该技术微调的模型能够带来一定改进。
英文摘要：
An all-too-present bottleneck for text classification model development is the need to annotate training data and this need is multiplied for multilingual classifiers. Fortunately, contemporary machine translation models are both easily accessible and have dependable translation quality, making it possible to translate labeled training data from one language into another. Here, we explore the effects of using machine translation to fine-tune a multilingual model for a classification task across multiple languages. We also investigate the benefits of using a novel technique, originally proposed in the field of image captioning, to account for potential negative effects of tuning models on translated data. We show that translated data are of sufficient quality to tune multilingual classifiers and that this novel loss technique is able to offer some improvement over models tuned without it.
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。
