# Cross-lingual Spoken Language Understanding with Regularized Representation Alignment

arXiv: https://arxiv.org/abs/2009.14510 · HTML: https://mlsanity.com/paper/2009.14510/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2020.

## Built on by (most cited first, 5 of 5)

- [Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding](https://mlsanity.com/paper/2109.01583/) (2021)
- [Label-aware Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding](https://mlsanity.com/paper/2205.03656/) (2022)
- [Call Larisa Ivanovna: Code-Switching Fools Multilingual NLU Models](https://mlsanity.com/paper/2109.14350/) (2021)
- [Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph](https://mlsanity.com/paper/2109.04400/) (2021)
- [LaDA: Latent Dialogue Action For Zero-shot Cross-lingual Neural Network Language Modeling](https://mlsanity.com/paper/2308.02903/) (2023)

## Abstract (arXiv)

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 with all the training data.