Gl-clef: A Global-local Contrastive Learning Framework For Cross-lingual Spoken Language Understanding

Abstract

Due to high data demands of current methods, attention to zero-shot cross-lingual spoken language understanding (SLU) has grown, as such approaches greatly reduce human annotation effort. However, existing models solely rely on shared parameters, which can only perform implicit alignment across languages. We present Global--Local Contrastive Learning Framework (GL-CLeF) to address this shortcoming. Specifically, we employ contrastive learning, leveraging bilingual dictionaries to construct multilingual views of the same utterance, then encourage their representations to be more similar than negative example pairs, which achieves to explicitly aligned representations of similar sentences across languages. In addition, a key step in GL-CLeF is a proposed Local and Global component, which achieves a fine-grained cross-lingual transfer (i.e., sentence-level Local intent transfer, token-level Local slot transfer, and semantic-level Global transfer across intent and slot). Experiments on Mul

Stats

• citations23
• S2 citations—
• github stars0
• HF likes0
• heat score10.35
• arxiv keyqin2022gl

Related papers

• Label-aware Multi-level Contrastive Learning For Cross-lingual Spoken Language Understanding (2022)6.34
• HC\(^2\)L: Hybrid And Cooperative Contrastive Learning For Cross-lingual Spoken Language Understanding (2024)4.52
• ML-LMCL: Mutual Learning And Large-margin Contrastive Learning For Improving ASR Robustness In Spoken Language Understanding (2023)0.00
• I\(^2\)KD-SLU: An Intra-inter Knowledge Distillation Framework For Zero-shot Cross-lingual Spoken Language Understanding (2023)0.00
• Unislu: Unified Spoken Language Understanding From Heterogeneous Cross-task Datasets (2025)0.00
• Leveraging Multilingual Self-supervised Pretrained Models For Sequence-to-sequence End-to-end Spoken Language Understanding (2023)0.00
• Exploring Fine-tuning Of Large Audio Language Models For Spoken Language Understanding Under Limited Speech Data (2025)0.00
• XLST: Cross-lingual Self-training To Learn Multilingual Representation For Low Resource Speech Recognition (2021)8.82