Cross-lingual Spoken Language Understanding With Regularized Representation Alignment
2020 · Zihan Liu, Genta Indra Winata, Peng Xu, et al.
Abstract
Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the performance sub-optimal. To cope with this issue, we propose a regularization approach to further align word-level and sentence-level representations across languages without any external resource. First, we regularize the representation of user utterances based on their corresponding labels. Second, we regularize the latent variable model (Liu et al., 2019) by leveraging adversarial training to disentangle the latent variables. Experiments on the cross-lingual spoken language understanding task show that our model outperforms current state-of-the-art methods in both few-shot and zero-shot scenarios, and our model, trained on a few-shot setting with only 3% of the target language training data, achieves comparable performance to the supervised training wi
Authors
(none)
Tags
Stats
Related papers
- HIT-SCIR At MMNLU-22: Consistency Regularization For Multilingual Spoken Language Understanding (2023)2.26
- HC\(^2\)L: Hybrid And Cooperative Contrastive Learning For Cross-lingual Spoken Language Understanding (2024)4.52
- Enhance Audio Generation Controllability Through Representation Similarity Regularization (2023)0.00
- Label-aware Multi-level Contrastive Learning For Cross-lingual Spoken Language Understanding (2022)6.34
- XLST: Cross-lingual Self-training To Learn Multilingual Representation For Low Resource Speech Recognition (2021)8.82
- Bidirectional Representations For Low Resource Spoken Language Understanding (2022)0.00
- Gl-clef: A Global-local Contrastive Learning Framework For Cross-lingual Spoken Language Understanding (2022)10.35
- Unsupervised Cross-lingual Representation Learning For Speech Recognition (2020)18.91