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 1708.08712cs.CL
收藏

多领域场景下的神经机器翻译训练

Neural Machine Translation Training in a Multi-Domain Scenario

Qatar Computing Research Institute -- HBKU(卡塔尔计算研究所——哈马德·本·哈利法大学);MIT Computer Science and Artificial Intelligence Laboratory(麻省理工学院计算机科学与人工智能实验室)

Hassan Sajjad, Nadir Durrani, Fahim Dalvi, Yonatan Belinkov, Stephan Vogel

摘要:

在本文中,我们探索替代方法来训练神经机器翻译系统在多领域的情况下。我们研究数据拼接(微调),模型堆叠(多级微调),数据选择和多模型集成。我们的研究结果表明,最好的翻译质量可以通过建立一个初始系统上的可用域外数据的串联,然后微调它的域内数据。当训练从最远的域外数据开始,然后模型根据下一个最远的域进行增量微调时,模型堆叠效果最好。数据选择并没有给出最佳结果,但可以被视为训练时间和翻译质量之间的适当折衷。不同个体模型的加权集合比数据选择更好。在没有时间对已经训练好的模型进行微调的情况下,这是有益的。

英文摘要:

In this paper, we explore alternative ways to train a neural machine translation system in a multi-domain scenario. We investigate data concatenation (with fine tuning), model stacking (multi-level fine tuning), data selection and multi-model ensemble. Our findings show that the best translation quality can be achieved by building an initial system on a concatenation of available out-of-domain data and then fine-tuning it on in-domain data. Model stacking works best when training begins with the furthest out-of-domain data and the model is incrementally fine-tuned with the next furthest domain and so on. Data selection did not give the best results, but can be considered as a decent compromise between training time and translation quality. A weighted ensemble of different individual models performed better than data selection. It is beneficial in a scenario when there is no time for fine-tuning an already trained 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。

↑