论文标题
NLP中的神经无监督域的适应---调查
Neural Unsupervised Domain Adaptation in NLP---A Survey
论文作者
论文摘要
深度神经网络擅长从标记的数据学习并获得最先进的结果，其中包括各种自然语言处理任务。相比之下，从未标记的数据中学习，尤其是在域转移下，仍然是一个挑战。在最新进展中，在本调查中，我们回顾了不需要标记为目标域数据的神经无监督的域适应技术。这是一个更具挑战性但更广泛的设置。我们概述了从早期的传统非神经方法到预训练的模型转移的方法。我们还重新审视了域的概念，我们发现了受到最关注的自然语言处理任务的偏见。最后，我们概述了未来的方向，尤其是对未来NLP的分布概括的广泛需求。
Deep neural networks excel at learning from labeled data and achieve state-of-the-art resultson a wide array of Natural Language Processing tasks. In contrast, learning from unlabeled data, especially under domain shift, remains a challenge. Motivated by the latest advances, in this survey we review neural unsupervised domain adaptation techniques which do not require labeled target domain data. This is a more challenging yet a more widely applicable setup. We outline methods, from early traditional non-neural methods to pre-trained model transfer. We also revisit the notion of domain, and we uncover a bias in the type of Natural Language Processing tasks which received most attention. Lastly, we outline future directions, particularly the broader need for out-of-distribution generalization of future NLP.
