Concept Transfer Learning for Adaptive Language Understanding

Semantic transfer is an important problem of the language understanding (LU), which is about how the recognition pattern of a semantic concept benefits other associated concepts. In this paper, we propose a new semantic representation based on combinatory concepts. Semantic slot is represented as a composition of different atomic concepts in different semantic dimensions. Specifically, we propose the concept transfer learning methods for extending combinatory concepts in LU. The concept transfer learning makes use of the common ground of combinatory concepts shown in the literal description. Our methods are applied to two adaptive LU problems: semantic slot refinement and domain adaptation, and respectively evaluated on two benchmark LU datasets: ATIS and DSTC 2&3. The experiment results show that the concept transfer learning is very efficient for semantic slot refinement and domain adaptation in the LU.