Existing works, including ELMO and BERT, have revealed the importance of pre-training for NLP tasks. While there does not exist a single pre-training model that works best in all cases, it is of necessity to develop a framework that is able to deploy various pre-training models efficiently. For this purpose, we propose an assemble-on-demand pre-training toolkit, namely Universal Encoder Representations (UER). UER is loosely coupled, and encapsulated with rich modules. By assembling modules on demand, users can either reproduce a state-of-the-art pre-training model or develop a pre-training model that remains unexplored. With UER, we have built a model zoo, which contains pre-trained models based on different corpora, encoders, and targets (objectives). With proper pre-trained models, we could achieve new state-of-the-art results on a range of downstream datasets.
@article{arxiv.1909.05658,
title = {UER: An Open-Source Toolkit for Pre-training Models},
author = {Zhe Zhao and Hui Chen and Jinbin Zhang and Xin Zhao and Tao Liu and Wei Lu and Xi Chen and Haotang Deng and Qi Ju and Xiaoyong Du},
journal= {arXiv preprint arXiv:1909.05658},
year = {2019}
}