Paradigm Shift in Natural Language Processing

查看全文 作　　者：Tian-Xiang [1,2]Sun;Xiang-Yang [1,2]Liu;Xi-Peng [1,2]Qiu;Xuan-Jing [1,2]Huang

机构地区：[1]School of Computer Science,Fudan University,Shanghai 200438,China;[2]Shanghai Key Laboratory of Intelligent Information Processing,Fudan University,Shanghai 200438,China

出　　处：《Machine Intelligence Research》索引2022年第19卷第3期,共15页

基　　金：supported by National Natural Science Foundation of China(No.62022027). 摘　　要：In the era of deep learning, modeling for most natural language processing (NLP) tasks has converged into several mainstream paradigms. For example, we usually adopt the sequence labeling paradigm to solve a bundle of tasks such as POS-tagging, named entity recognition (NER), and chunking, and adopt the classification paradigm to solve tasks like sentiment analysis. With the rapid progress of pre-trained language models, recent years have witnessed a rising trend of paradigm shift, which is solving one NLP task in a new paradigm by reformulating the task. The paradigm shift has achieved great success on many tasks and is becoming a promising way to improve model performance. Moreover, some of these paradigms have shown great potential to unify a large number of NLP tasks, making it possible to build a single model to handle diverse tasks. In this paper, we review such phenomenon of paradigm shifts in recent years, highlighting several paradigms that have the potential to solve different NLP tasks. 关键词：Natural language processing pre-trained language models deep learning sequence-to-sequence paradigm shift

相关文献

参考文献（95）
引证文献（11）
耦合文献（202）

参考文献(95)

引证文献(11)

耦合文献(202)

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费

Paradigm Shift in Natural Language Processing

参考文献(95)

引证文献(11)

耦合文献(202)

用户提示