# Source-Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language

arXiv: https://arxiv.org/abs/1808.06167 · HTML: https://mlsanity.com/paper/1808.06167/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2018.

## Built on by (most cited first, 3 of 3)

- [XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2210.13693/) (2022)
- [Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook](https://mlsanity.com/paper/2210.13623/) (2022)
- [Low-Rank and Sparse Model Merging for Multi-Lingual Speech Recognition and Translation](https://mlsanity.com/paper/2502.17380/) (2025)

## Abstract (arXiv)

To deploy a spoken language understanding (SLU) model to a new language, language transferring is desired to avoid the trouble of acquiring and labeling a new big SLU corpus. Translating the original SLU corpus into the target language is an attractive strategy. However, SLU corpora consist of plenty of semantic labels (slots), which general-purpose translators cannot handle well, not to mention additional culture differences. This paper focuses on the language transferring task given a tiny in-domain parallel SLU corpus. The in-domain parallel corpus can be used as the first adaptation on the general translator. But more importantly, we show how to use reinforcement learning (RL) to further finetune the adapted translator, where translated sentences with more proper slot tags receive higher rewards. We evaluate our approach on Chinese to English language transferring for SLU systems. The experimental results show that the generated English SLU corpus via adaptation and reinforcement learning gives us over 97% in the slot F1 score and over 84% accuracy in domain classification. It demonstrates the effectiveness of the proposed language transferring method. Compared with naive translation, our proposed method improves domain classification accuracy by relatively 22%, and the slot filling F1 score by relatively more than 71%.