Large-scale pretrained language models have led to dramatic improvements in text generation. Impressive performance can be achieved by finetuning only on a small number of instances (few-shot setting). Nonetheless, almost all previous work simply applies random sampling to select the few-shot training instances. Little to no attention has been paid to the selection strategies and how they would affect model performance. In this work, we present a study on training instance selection in few-shot neural text generation. The selection decision is made based only on the unlabeled data so as to identify the most worthwhile data points that should be annotated under some budget of labeling cost. Based on the intuition that the few-shot training instances should be diverse and representative of the entire data distribution, we propose a simple selection strategy with K-means clustering. We show that even with the naive clustering-based approach, the generation models consistently outperform random sampling on three text generation tasks: data-to-text generation, document summarization and question generation. We hope that this work will call for more attention on this largely unexplored area.
Instance Relation Learning Network with Label Knowledge Propagation for Few-shot Multi-label Intent Detection
Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University, Beijing, China(高可信软件技术重点实验室(教育部)、计算机科学学院、北京大学,北京,中国);Research Center for Computational Social Science, Peking University, Beijing, China(计算社会科学研究中心、北京大学,北京,中国);Institute of Computational Social Science, Peking University, Qingdao, China(计算社会科学研究院、北京大学,青岛,中国);Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China(系统工程与工程管理系、香港中文大学,香港,中国)
Automatic Combination of Sample Selection Strategies for Few-Shot Learning
Faculty of Information Technology, Brno University of Technology(布拉格技术学院,布拉格技术大学);Kempelen Institute of Intelligent Technologies(智能技术研究所);Eindhoven University of Technology(埃因霍温技术大学)
College of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院);Alibaba Cloud Computing(阿里巴巴云计算);Shanghai Jiao Tong University(上海交通大学);College of Software, Zhejiang University(浙江大学软件学院)
Few-shot Named Entity Recognition via Superposition Concept Discrimination
University of Chinese Academy of Sciences(中国科学院大学);State Key Laboratory of Computer Science(计算机科学国家重点实验室);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);Ricoh Software Research Center Beijing Co., Ltd(理光软件研究中心(北京)有限公司)
Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification
National Engineering Laboratory for Speech and Language Information Processing(语音及语言信息处理国家工程实验室);University of Science and Technology of China(中国科学技术大学)
Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classification
Faculty of Information Technology, Brno University of Technology(布尔诺理工大学信息技术学院);Kempelen Institute of Intelligent Technologies(肯佩伦智能技术研究所);University of Pittsburgh(匹兹堡大学)
Few-Shot Domain Adaptation for Named-Entity Recognition via Joint Constrained k-Means and Subspace Selection
Université de Brest(布雷斯特大学);Université Paris-Saclay(巴黎萨克雷大学);Data Analytics Solutions, SCOR(SCOR数据分析解决方案部);INSA Rennes(雷恩国立应用科学学院);IRISA(IRISA研究所);Inria(法国国家信息与自动化研究所);CNRS(法国国家科学研究中心);Université de Rennes(雷恩大学)
Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning
Graduate School of Information Science(信息科学研究生院);Technology Hokkaido University Hokkaido, Japan(技术 Hokkaido 大学 Hokkaido, Japan);National Institute of Information(信息国家研究所);Faculty of Information Science(信息科学学院)