Timezone: »

Model-Level Dual Learning
Yingce Xia · Xu Tan · Fei Tian · Tao Qin · Nenghai Yu · Tie-Yan Liu

Wed Jul 11 06:20 AM -- 06:30 AM (PDT) @ Victoria
Many artificial intelligence tasks appear in dual forms like English$\leftrightarrow$French translation and speech$\leftrightarrow$text transformation. Existing dual learning schemes, which are proposed to solve a pair of such dual tasks, explore how to leverage such dualities from data level. In this work, we propose a new learning framework, model-level dual learning, which takes duality of tasks into consideration while designing the architectures for the primal/dual models, and ties the model parameters that playing similar roles in the two tasks. We study both symmetric and asymmetric model-level dual learning. Our algorithms achieve significant improvements on neural machine translation and sentiment analysis.

Author Information

Yingce Xia (University of Science and Technology of China)
Xu Tan (Microsoft Research)
Fei Tian (Microsoft Research)
Tao Qin (Microsoft Research Asia)
Nenghai Yu (USTC)
Tie-Yan Liu (Microsoft)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors