We present MT-DNN, an open-source natural language understanding (NLU) toolkit that makes it easy for researchers and developers to train customized deep learning models. Built upon PyTorch and Transformers, MT-DNN is designed to facilitate rapid customization for a broad spectrum of NLU tasks, using a variety of objectives (classification, regression, structured prediction) and text encoders (e.g., RNNs, BERT, RoBERTa, UniLM). A unique feature of MT-DNN is its built-in support for robust and transferable learning using the adversarial multi-task learning paradigm. To enable efficient production deployment, MT-DNN supports multi-task knowledge distillation, which can substantially compress a deep neural model without significant performance drop. We demonstrate the effectiveness of MT-DNN on a wide range of NLU applications across general and biomedical domains. The software and pre-trained models will be publicly available at https://github.com/namisan/mt-dnn.
@article{arxiv.2002.07972,
title = {The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding},
author = {Xiaodong Liu and Yu Wang and Jianshu Ji and Hao Cheng and Xueyun Zhu and Emmanuel Awa and Pengcheng He and Weizhu Chen and Hoifung Poon and Guihong Cao and Jianfeng Gao},
journal= {arXiv preprint arXiv:2002.07972},
year = {2020}
}