HierarchicalContrast: A Coarse-to-Fine Contrastive Learning Framework for Cross-Domain Zero-Shot Slot Filling

In task-oriented dialogue scenarios, crossdomain zero-shot slot filling plays a vital role in leveraging source domain knowledge to learn a model with high generalization ability in unknown target domain where annotated data is unavailable. However, the existing stateof-the-art zero-shot slot filling methods have limited generalization ability in target domain, they only show effective knowledge transfer on seen slots and perform poorly on unseen slots. To alleviate this issue, we present a novel Hierarchical Contrastive Learning Framework (HiCL) for zero-shot slot filling. Specifically, we propose a coarse-to fine-grained contrastive learning based on Gaussian-distributed embedding to learn the generalized deep semantic relations between utterance-tokens, by optimizing inter-and intra-token distribution distance. This encourages HiCL to generalize to slot types unseen at training phase. Furthermore, we present a new iterative label set semantics inference method to unbiasedly and separately evaluate the performance of unseen slot types which entangled with their counterparts (i.e., seen slot types) in the previous zeroshot slot filling evaluation methods. The extensive empirical experiments 1 on four datasets demonstrate that the proposed method achieves comparable or even better performance than the current state-of-the-art zero-shot slot filling approaches.