arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.00632cs.CL
收藏

NLP中的神经元无监督领域自适应

Neural Unsupervised Domain Adaptation in NLP---A Survey

University of Trento(特伦托大学);ITU Copenhagen(哥本哈根信息技术大学)

Alan Ramponi, Barbara Plank

摘要:

深度神经网络擅长从标记数据中学习,并在各种自然语言处理任务中实现最先进的结果。相比之下,从未标记数据中学习,特别是在域转移下,仍然是一个挑战。受最新进展的启发,在这次调查中,我们回顾了神经无监督领域自适应技术,不需要标记的目标域数据。这是一个更具挑战性但适用范围更广的设置。我们概述了从早期传统的非神经方法到预训练模型转移的方法。我们还重新审视了域的概念,我们发现了最受关注的自然语言处理任务类型的偏见。最后,我们概述了未来的发展方向,特别是对未来NLP的分布外泛化的更广泛需求。

英文摘要:

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.

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。

↑