Timezone: »
Many supervised learning tasks are emerged in dual forms, e.g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation. Two dual tasks have intrinsic connections with each other due to the probabilistic correlation between their models. This connection is, however, not effectively utilized today, since people usually train the models of two dual tasks separately and independently. In this work, we propose training the models of two dual tasks simultaneously, and explicitly exploiting the probabilistic correlation between them to regularize the training process. For ease of reference, we call the proposed approach dual supervised learning. We demonstrate that dual supervised learning can improve the practical performances of both tasks, for various applications including machine translation, image processing, and sentiment analysis.
Author Information
Yingce Xia (University of Science and Technology of China)
Tao Qin (Microsoft Research Asia)
Wei Chen (Microsoft Research)
Jiang Bian (Microsoft Research)
Nenghai Yu (USTC)
Tie-Yan Liu (Microsoft)
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Talk: Dual Supervised Learning »
Mon Aug 7th 03:30 -- 03:48 AM Room C4.6 & C4.7
More from the Same Authors
-
2020 Poster: Sequence Generation with Mixed Representations »
Lijun Wu · Shufang Xie · Yingce Xia · Yang Fan · Jian-Huang Lai · Tao Qin · Tie-Yan Liu -
2019 Poster: MASS: Masked Sequence to Sequence Pre-training for Language Generation »
Kaitao Song · Xu Tan · Tao Qin · Jianfeng Lu · Tie-Yan Liu -
2019 Poster: Adaptive Regret of Convex and Smooth Functions »
Lijun Zhang · Tie-Yan Liu · Zhi-Hua Zhou -
2019 Poster: Efficient Training of BERT by Progressively Stacking »
Linyuan Gong · Di He · Zhuohan Li · Tao Qin · Liwei Wang · Tie-Yan Liu -
2019 Poster: Almost Unsupervised Text to Speech and Automatic Speech Recognition »
Yi Ren · Xu Tan · Tao Qin · Sheng Zhao · Zhou Zhao · Tie-Yan Liu -
2019 Oral: Efficient Training of BERT by Progressively Stacking »
Linyuan Gong · Di He · Zhuohan Li · Tao Qin · Liwei Wang · Tie-Yan Liu -
2019 Oral: MASS: Masked Sequence to Sequence Pre-training for Language Generation »
Kaitao Song · Xu Tan · Tao Qin · Jianfeng Lu · Tie-Yan Liu -
2019 Oral: Adaptive Regret of Convex and Smooth Functions »
Lijun Zhang · Tie-Yan Liu · Zhi-Hua Zhou -
2019 Oral: Almost Unsupervised Text to Speech and Automatic Speech Recognition »
Yi Ren · Xu Tan · Tao Qin · Sheng Zhao · Zhou Zhao · Tie-Yan Liu -
2018 Poster: Towards Binary-Valued Gates for Robust LSTM Training »
Zhuohan Li · Di He · Fei Tian · Wei Chen · Tao Qin · Liwei Wang · Tie-Yan Liu -
2018 Oral: Towards Binary-Valued Gates for Robust LSTM Training »
Zhuohan Li · Di He · Fei Tian · Wei Chen · Tao Qin · Liwei Wang · Tie-Yan Liu -
2018 Poster: Model-Level Dual Learning »
Yingce Xia · Xu Tan · Fei Tian · Tao Qin · Nenghai Yu · Tie-Yan Liu -
2018 Oral: Model-Level Dual Learning »
Yingce Xia · Xu Tan · Fei Tian · Tao Qin · Nenghai Yu · Tie-Yan Liu -
2017 Poster: Asynchronous Stochastic Gradient Descent with Delay Compensation »
Shuxin Zheng · Qi Meng · Taifeng Wang · Wei Chen · Nenghai Yu · Zhiming Ma · Tie-Yan Liu -
2017 Talk: Asynchronous Stochastic Gradient Descent with Delay Compensation »
Shuxin Zheng · Qi Meng · Taifeng Wang · Wei Chen · Nenghai Yu · Zhiming Ma · Tie-Yan Liu