Label-Aware Multi-Level Contrastive Learning for Cross-Lingual Intent Recognition in Low-Resource Languages on XTREME

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: To what extent can label-aware multi-level contrastive learning improve cross-lingual intent recognition in non-English low-resource languages when evaluated on the XTREME benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.8/10.