基于近似目标边的特征衰减算法的数据选择
Data Selection with Feature Decay Algorithms Using an Approximated Target Side
摘要:
应用于神经机器翻译(NMT)的数据选择技术旨在通过检索句子的子集以用作训练数据来提高模型的性能。可能的数据选择技术之一是转换学习方法,它基于测试集(即待翻译的文档)选择数据。迄今为止,这些方法的局限性在于,使用源端测试集本身并不能保证选择具有正确翻译的句子,或者在给定测试集域的情况下选择合适的翻译。一些语料库,如字幕语料库,可能包含由于本地化或长度限制而导致翻译不准确的平行句子。为了尝试解决这个问题,在本文中,我们建议在选择合适的训练模型的训练对时,除了源端之外,还使用近似的目标端。这个近似的目标端是通过预翻译源端来构建的。在这项工作中,我们探讨了一个特定的数据选择方法,称为特征衰减算法(FDA)的一般思想的性能。我们训练德-英NMT模型的数据选择使用测试集(源),近似的目标侧,以及两者的混合。我们的研究结果表明,使用FDA的输出组合(使用测试集和近似的目标侧)建立的模型比单独使用测试集的模型表现更好。我们获得了超过1.5个BLEU点的统计学显着改善,超过所有数据训练的模型,超过0.5个BLEU点,超过仅使用源端信息的强大FDA基线。
英文摘要:
Data selection techniques applied to neural machine translation (NMT) aim to increase the performance of a model by retrieving a subset of sentences for use as training data. One of the possible data selection techniques are transductive learning methods, which select the data based on the test set, i.e. the document to be translated. A limitation of these methods to date is that using the source-side test set does not by itself guarantee that sentences are selected with correct translations, or translations that are suitable given the test-set domain. Some corpora, such as subtitle corpora, may contain parallel sentences with inaccurate translations caused by localization or length restrictions. In order to try to fix this problem, in this paper we propose to use an approximated target-side in addition to the source-side when selecting suitable sentence-pairs for training a model. This approximated target-side is built by pre-translating the source-side. In this work, we explore the performance of this general idea for one specific data selection approach called Feature Decay Algorithms (FDA). We train German-English NMT models on data selected by using the test set (source), the approximated target side, and a mixture of both. Our findings reveal that models built using a combination of outputs of FDA (using the test set and an approximated target side) perform better than those solely using the test set. We obtain a statistically significant improvement of more than 1.5 BLEU points over a model trained with all data, and more than 0.5 BLEU points over a strong FDA baseline that uses source-side information only.
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。