低资源机器翻译中反向翻译的多样性探索
Exploring Diversity in Back Translation for Low-Resource Machine Translation
AI总结：
本研究提出区分词汇与句法多样性的框架及新指标，实证发现核采样生成反向翻译性能更优，且词汇多样性比句法多样性更重要。
摘要：
反向翻译是提升神经机器翻译系统性能最广泛使用的方法之一。近期研究试图通过增加生成翻译的“多样性”来增强该方法的有效性。我们认为，先前工作中用于量化“多样性”的定义和指标尚不充分。本研究提出了一个更细致的框架来理解训练数据中的多样性，将其区分为词汇多样性和句法多样性。我们提出了衡量这些不同多样性方面的新指标，并针对低资源英语↔土耳其语和中资源英语↔冰岛语，对这些多样性类型对最终神经机器翻译模型性能的影响进行了实证分析。我们的发现表明，使用核采样生成反向翻译能带来更高的最终模型性能，且这种生成方法具有较高的词汇多样性和句法多样性。我们还发现，对于反向翻译性能，词汇多样性比句法多样性更为重要。
英文摘要：
Back translation is one of the most widely used methods for improving the performance of neural machine translation systems. Recent research has sought to enhance the effectiveness of this method by increasing the 'diversity' of the generated translations. We argue that the definitions and metrics used to quantify 'diversity' in previous work have been insufficient. This work puts forward a more nuanced framework for understanding diversity in training data, splitting it into lexical diversity and syntactic diversity. We present novel metrics for measuring these different aspects of diversity and carry out empirical analysis into the effect of these types of diversity on final neural machine translation model performance for low-resource English$\leftrightarrow$Turkish and mid-resource English$\leftrightarrow$Icelandic. Our findings show that generating back translation using nucleus sampling results in higher final model performance, and that this method of generation has high levels of both lexical and syntactic diversity. We also find evidence that lexical diversity is more important than syntactic for back translation performance.
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。
