Neural Automatic Evaluation of Machine Translation Method Combined with XLM Word Representation

扫码查看

原文链接

NETL

中文摘要：机器译文自动评价对机器翻译的发展和应用起着重要的促进作用，它一般通过计算机器译文和人工参考译文的相似度来度量机器译文的质量。该文通过跨语种预训练语言模型XLM将源语言句子、机器译文和人工参考译文映射到相同的语义空间，结合分层注意力和内部注意力提取源语言句子与机器译文、机器译文与人工参考译文以及源语言句子与人工参考译文之间差异特征，并将其融入到基于Bi-LSTM神经译文自动评价方法中。在WMT，19译文自动评价数据集上的实验结果表明，融合XLM词语表示的神经机器译文自动评价方法显著提高了其与人工评价的相关性。

外文摘要：The automatic evaluation of machine translation plays an important role in promoting the development and application of machine translation。 It generally measures the quality of machine translation through calculating the similarity between machine translation and its reference。 This paper uses the cross-lingual language model XLM to map source sentences， machine translations and reference to the same semantic s-pace， and combines layer-wise attention and intra attention to extract the difference features from source sentences and machine translations， machine translations and its references， source sentences and its references， then integrates them into the automatic evaluation method based on neural network Bi-LSTM。 The experimental results on the dataset of WMT'19 Metrics task show that the neural automatic evaluation method of machine translation combined with XLM word representation significantly improves its correlation with human judgments。

外文关键词：

machine translationautomatic evaluation of machine translationcross-lingual language modeldifference features

作者：

Wei Hu、Maoxi Li、Bailian Qiu、Mingwen Wang

展开 >

作者单位：

School of Computer Information Engineering, Jiangxi Normal University Nanchang, 330022, China

会议名称：

Chinese National Conference on Computational Linguistic

会议地点：

Hohhot(CN)

会议母体文献：

20th Chinese National Conference on Computational Linguistic

页码：

13-22

出版时间：

2021