Label-Aware Multi-Level Contrastive Learning for Robust Cross-Lingual Spoken Language Understanding Against Speech Errors

Despite the great success of spoken language understanding (SLU) in high-resource languages, it remains challenging in low-resource languages mainly due to the lack of labeled training data. The recent multilingual code-switching approach achieves better alignments of model representations across languages by constructing a mixed-language context in zero-shot cross-lingual SLU. However, current code-switching methods are limited to implicit alignment and disregard the inherent semantic structure in SLU, i.e., the hierarchical inclusion of utterances, slots and words. In this paper, we propose

Research goal: What is the impact of label-aware multi-level contrastive learning on model robustness against speech recognition errors in cross-lingual spoken language understanding tasks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10.