Abstract
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.
Abstract (translated)
在本文中,我们实证调查应用词级权重,以适应神经机器翻译到电子商务领域,其中小电子商务数据集和大量的域外数据集是可用的。为了在域内挖掘域外数据集中的类词,我们使用了一个特定于域和非特定于域的语言模型,然后进行平滑和二进制量化来计算词权重。基线模型是在混合的域内和域外数据集上训练的。对英汉电子商务领域翻译的实验结果表明,与不加词权的继续训练相比,它提高了mt的质量,达到2.11%的绝对值和1.59%的绝对值。我们还使用域内数据的微调对模型进行了培训。预先训练一个有单词权重的模型可以分别提高1.24%的绝对值和1.64%的ter值。
URL
https://arxiv.org/abs/1906.03129