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 1906.03129cs.CLcs.AI
收藏

基于词的神经机器翻译领域自适应

Word-based Domain Adaptation for Neural Machine Translation

eBay Inc.(易趣公司)

Shen Yan, Leonard Dahlmann, Pavel Petrushkov, Sanjika Hewavitharana, Shahram Khadivi

摘要:

在本文中,我们实证研究了应用单词级权重来使神经机器翻译适应电子商务领域,其中小型电子商务数据集和大型域外数据集可用。为了在领域外数据集中挖掘领域内相似的词,我们通过使用特定领域和非特定领域的语言模型,然后进行平滑和二进制量化来计算词的权重。基线模型在域内和域外混合数据集上进行训练。在英汉电子商务领域翻译中的实验结果表明,与不使用词权重的持续训练相比,该方法将机器翻译质量提高了2.11%的BLEU绝对值和1.59%的TER。我们还使用对域内数据的微调来训练模型。使用单词权重预训练模型可以分别将微调提高到1.24% BLEU绝对值和1.64% TER。

英文摘要:

In this paper, we empirically investigate applying word-level weights to adapt neural machine translation to e-commerce domains, where small e-commerce datasets and large out-of-domain datasets are available. In order to mine in-domain like words in the out-of-domain datasets, we compute word weights by using a domain-specific and a non-domain-specific language model followed by smoothing and binary quantization. The baseline model is trained on mixed in-domain and out-of-domain datasets. Experimental results on English to Chinese e-commerce domain translation show that compared to continuing training without word weights, it improves MT quality by up to 2.11% BLEU absolute and 1.59% TER. We have also trained models using fine-tuning on the in-domain data. Pre-training a model with word weights improves fine-tuning up to 1.24% BLEU absolute and 1.64% TER, respectively.

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。

↑