arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1908.09532cs.CL
收藏

用于神经机器翻译微调的直接数据选择算法

Transductive Data-Selection Algorithms for Fine-Tuning Neural Machine Translation

ADAPT Centre(ADAPT中心);Dublin City University(都柏林城市大学)

Alberto Poncelas, Gideon Maillette de Buy Wenniger, Andy Way

摘要:

机器翻译模型经过训练,可以将各种文档从一种语言翻译成另一种语言。然而,针对文档的特定特征专门训练的模型往往表现得更好。微调是使NMT模型适应某些领域的技术。在这项工作中,我们希望使用这种技术来调整模型以适应给定的测试集。特别是,我们使用的是转换数据选择算法,它利用测试集的信息,从一个更大的并行集检索句子。在模型在翻译时可用的情况下(当提供测试集时),它可以用一小部分数据进行调整,从而实现比通用模型或域适应模型更好的性能。

英文摘要:

Machine Translation models are trained to translate a variety of documents from one language into another. However, models specifically trained for a particular characteristics of the documents tend to perform better. Fine-tuning is a technique for adapting an NMT model to some domain. In this work, we want to use this technique to adapt the model to a given test set. In particular, we are using transductive data selection algorithms which take advantage the information of the test set to retrieve sentences from a larger parallel set. In cases where the model is available at translation time (when the test set is provided), it can be adapted with a small subset of data, thereby achieving better performance than a generic model or a domain-adapted model.

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。

↑