持续学习——Neural Topic Modeling with Continual Lifelong Learning——ICML2020

Abstract

continual learning+ unsupervised topic modeling《Lifelong machine learning for natural language processing, EMNLP2016》《Topic modeling using topics from many domains, lifelong learning and big data， ICML2014》
难点data sparsity（in a small collection of short documents and thus, generate incoherent topics and sub-optimal document representations）；from several sources to deal with the sparse data;

Introduction

continual learning for supervised NLP tasks

Conclusion

a stream of document collections; 通过information retrieval, topic coherence and generalization

Key points: 什么是unsupervised topic modeling, discover topics from document collections; 一种写结合continual learning的论文范式；
code开源