Concept Transfer Learning for Adaptive Language Understanding
This work addresses adaptation challenges in language understanding for tasks like value set mismatch and domain adaptation, offering incremental improvements over existing methods.
The paper tackles the problem of data sparsity in language understanding adaptation due to literal concept definition differences by proposing a concept transfer learning approach with hierarchical semantic representation, achieving state-of-the-art performance with an F1-score of 96.08% on the ATIS benchmark using only lexicon features.
Concept definition is important in language understanding (LU) adaptation since literal definition difference can easily lead to data sparsity even if different data sets are actually semantically correlated. To address this issue, in this paper, a novel concept transfer learning approach is proposed. Here, substructures within literal concept definition are investigated to reveal the relationship between concepts. A hierarchical semantic representation for concepts is proposed, where a semantic slot is represented as a composition of {\em atomic concepts}. Based on this new hierarchical representation, transfer learning approaches are developed for adaptive LU. The approaches are applied to two tasks: value set mismatch and domain adaptation, and evaluated on two LU benchmarks: ATIS and DSTC 2\&3. Thorough empirical studies validate both the efficiency and effectiveness of the proposed method. In particular, we achieve state-of-the-art performance ($F_1$-score 96.08\%) on ATIS by only using lexicon features.