Curriculum learning has shown promising improvements in multiple domains by training machine learning models from easy samples to hard ones. Previous works which either design rules or train models for scoring the difficulty highly rely on task-specific expertise, and cannot generalize. Inspired by the "easy-to-hard" intuition, we propose to do in-sample curriculum learning for natural language generation tasks. Our learning strategy starts training the model to generate the last few words, i.e., do sequence completion, and gradually extends to generate the whole output sequence. Comprehensive experiments show that it generalizes well to different tasks and achieves significant improvements over strong baselines.
Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation
Tsinghua University（清华大学）；OPPO Mobile Telecommunications Corp., Ltd（OPPO移动通信有限公司）；China Mobile Research Institute（中国移动研究院）；Tsinghua University-China Mobile Communications Group Co., Ltd. Joint Institute（清华大学-中国移动通信集团有限公司联合研究院）
Broader terms curriculum mapping: Using natural language processing and visual-supported communication to create representative program planning experiences
Escola Superior de Tecnologia de Setúbal（塞图巴尔高等技术学院）；Instituto Politécnico de Setúbal（塞图巴尔理工学院）；Escola Superior de Ciências Empresariais（高等企业科学学院）；Universidade Aberta（阿贝塔大学）
A SentiWordNet Strategy for Curriculum Learning in Sentiment Analysis
Language Technologies Research Center（语言技术研究中心）；Kohli Center on Intelligent Systems（科利智能系统中心）；International Institute of Information Technology, Hyderabad（海得拉巴国际信息技术学院）
SA-GCS: Semantic-Aware Gaussian Curriculum Scheduling for UAV Vision-Language Navigation
Sun Yat-Sen University（中山大学）；DP Technology（深势科技）；Beijing University Of Posts and Telecommunications（北京邮电大学）；Beihang University（北京航空航天大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；XPENG（小鹏）；Chulalongkorn University（朱拉隆功大学）
Combining Axiom Injection and Knowledge Base Completion for Efficient Natural Language Inference
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Ochanomizu University（御茶水女子大学）；Artificial Intelligence Research Center, AIST（产业技术综合研究所人工智能研究中心）
A Knowledge-Injected Curriculum Pretraining Framework for Question Answering
University of Science and Technology of China（中国科学技术大学）；Guangdong OPPO Mobile Telecommunications Corp., Ltd（广东欧珀移动通信有限公司）；State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）
Train Long, Think Short: Curriculum Learning for Efficient Reasoning
King Abdullah University of Science and Technology (KAUST), Saudi Arabia（卡布尔大学科学与技术大学）；Massachusetts Institute of Technology (MIT), Cambridge, MA, USA（麻省理工学院）；Princeton University, Princeton, NJ, USA（普林斯顿大学）
Situated Dialogue Learning through Procedural Environment Generation
Georgia Institute of Technology（佐治亚理工学院）；Allen Institute for AI（艾伦人工智能研究所）
我们教目标驱动的代理交互式的行为和说话，在所处的环境中，通过训练生成的campaums。我们的代理人在LIGHT（Urbanek et al. 2019）中运行-这是一款大型众包幻想文本冒险游戏，其中代理人通过文本自然语言感知世界并与世界互动。在这种环境中，目标采取基于角色的任务形式，包括人物角色和动机。我们通过学习程序化地生成额外的新文本世界和任务来增强LIGHT，以创建一个稳步增加难度的课程，用于训练代理实现这些目标。特别是，我们根据原始训练分布中任务的稀有性来衡量课程难度--一个更容易的环境是一个更有可能在未增强的数据集中找到的环境。一项消融研究表明，这种从分布尾部学习的方法可以显著提高泛化能力，这是通过对从未见过的任务的zero-shot性能来衡量的。
