本文研究个性化检索式对话系统，传统的个性化方法利用persona编码增强context表示，然后再与response匹配，而本文提出了DIM模型，核心是context与response，persona与response进行双匹配。 paper: https://drive.google.com/open?id=1WIBSG2pRGhpVmkV4OGNx0X2xQzSu-v2Ccode: https://github.com/JasonForJoy/DIMsource: EMNLP 2019
本文提出了一种少样本下的元学习方法，用于文本分类，在多个数据集上取得较好效果。 paper: https://drive.google.com/open?id=19HtiZOH1jKWtEu_pq38wVYtYOwNIvPiPcode: https://github.com/YujiaBao/Distributional-Signaturessource: Work in Progress for ICLR2020
Introduction任务导向型对话系统用于帮助用户完成某个任务如查电影、找餐馆等，它一般由四个模块组成：自然语言理解模块（Natural Language Understanding, NLU）、对话状态跟踪模块（Dialog State Tracking, DST）、对话策略模块（Dialog Policy, DP）和自然语言生成模块（Natural language Generation
Meta-learning, also known as “learning to learn”, intends to design models that can learn new skills or adapt to new environments rapidly with a few training examples. There are three common approaches: 1) learn an efficient distance metric (metric-based); 2) use (recurrent) network with external or internal memory (model-based); 3) optimize the model parameters explicitly for fast learning (optimization-based).