Low-shot Learning in Natural Language Processing

Low-shot Learning in Natural Language Processing
复制标题

DOI：
10.1109/cogmi50398.2020.00031
复制
发表时间：
2020-10
期刊：
2020 IEEE Second International Conference on Cognitive Machine Intelligence (CogMI)
影响因子：
--
通讯作者：
Congying Xia;Chenwei Zhang;Jiawei Zhang;Tingting Liang;Hao Peng-;Philip S. Yu
Congying Xia;Chenwei Zhang;Jiawei Zhang;Tingting Liang;Hao Peng-;Philip S. Yu
中科院分区：
其他
文献类型：
--
作者：
Congying Xia;Chenwei Zhang;Jiawei Zhang;Tingting Liang;Hao Peng-;Philip S. Yu

文献摘要

相似文献

本文研究自然语言处理（NLP）中的低注学习范式，其目的是提供能够适应新任务或新领域的能力，但标注数据有限，如零或很少的标注示例。具体来说，Low-shot学习统一了zero-shot和few-shot学习范式。针对不同的NLP任务（例如，意图检测和命名实体类型）讨论了各种低拍摄学习方法，包括基于胶囊的网络，数据增强方法和记忆网络。我们还为NLP中的低拍摄学习提供了潜在的未来方向。
This paper study the low-shot learning paradigm in Natural Language Processing (NLP), which aims to provide the ability that can adapt to new tasks or new domains with limited annotation data, like zero or few labeled examples. Specifically, Low-shot learning unifies the zero-shot and few-shot learning paradigm. Diverse low-shot learning approaches, including capsule-based networks, data-augmentation methods, and memory networks, are discussed for different NLP tasks, for example, intent detection and named entity typing. We also provide potential future directions for low-shot learning in NLP.