HC$^2$L: Hybrid and Cooperative Contrastive Learning for Cross-lingual Spoken Language Understanding

arXiv:2405.06204v1 Announce Type: new
Abstract: State-of-the-art model for zero-shot cross-lingual spoken language understanding performs cross-lingual unsupervised contrastive learning to achieve the label-agnostic semantic alignment between each utterance and its code-switched data. However, it ignores the precious intent/slot labels, whose label information is promising to help capture the label-aware semantics structure and then leverage supervised contrastive learning to improve both source and target languages' semantics. In this paper, we propose Hybrid and Cooperative Contrastive Learning to address this problem. Apart from …

abstract alignment art arxiv code cross-lingual cs.ai cs.cl data however hybrid information labels language language understanding semantic semantics spoken spoken language understanding state type understanding unsupervised zero-shot