arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.06951cs.CL
收藏

神经机器翻译领域自适应和多领域自适应研究综述

Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey

University of Cambridge(剑桥大学)

Danielle Saunders

摘要:

深度学习技术的发展使得神经机器翻译(NMT)模型变得非常强大,只要有足够的训练数据和训练时间。然而,系统在翻译来自具有不同风格或词汇的新领域的文本时会遇到困难。对域内数据的微调允许良好的领域自适应,但需要足够的相关双语数据。即使这是可用的,简单的微调可能会导致过度拟合新的数据和“灾难性遗忘”以前学到的行为。我们专注于强大的方法,领域自适应的NMT,特别是在一个系统可能需要跨多个域的翻译。我们将技术分为围绕数据选择或生成,模型架构,参数自适应过程和推理过程。最后,我们强调的好处领域自适应和多领域自适应技术的NMT研究的其他线路。

英文摘要:

The development of deep learning techniques has allowed Neural Machine Translation (NMT) models to become extremely powerful, given sufficient training data and training time. However, systems struggle when translating text from a new domain with a distinct style or vocabulary. Fine-tuning on in-domain data allows good domain adaptation, but requires sufficient relevant bilingual data. Even if this is available, simple fine-tuning can cause overfitting to new data and `catastrophic forgetting' of previously learned behaviour. We concentrate on robust approaches to domain adaptation for NMT, particularly where a system may need to translate across multiple domains. We divide techniques into those revolving around data selection or generation, model architecture, parameter adaptation procedure, and inference procedure. We finally highlight the benefits of domain adaptation and multi-domain adaptation techniques to other lines of NMT research.

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。

↑