Timezone: »

Dual Supervised Learning
Yingce Xia · Tao Qin · Wei Chen · Jiang Bian · Nenghai Yu · Tie-Yan Liu

Mon Aug 07 01:30 AM -- 05:00 AM (PDT) @ Gallery #48

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)

More from the Same Authors