发表机构
Qatar Computing Research Institute（卡塔尔计算研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Aslema 系统参与 NADI 2026 共享任务 5，通过微调模型及合成数据增强（含文化适配语句生成与语音克隆）提升性能，在官方测试集槽填充排第1、意图识别排第4，将公开脚本与合成数据集。
AI 中文摘要
我们展示了面向 NADI 2026 共享任务 5 的系统 Aslema，该任务包含意图识别和槽填充两个子任务。我们在零样本设置下评估了四个全功能大语言模型（omni LLMs），并将其与微调模型进行对比。结果表明，微调模型的表现始终优于零样本推理。我们进一步探索合成数据增强方法：利用大语言模型生成符合突尼斯 Derja 文化背景的语句，再通过语音克隆生成合成语音。加入该合成数据可提升两个子任务的性能。我们最终提交的系统基于 Qwen3-Omni-30B，采用原始数据与合成数据混合训练，在 devtest 划分集上实现了 86.8% 的意图识别准确率和 34.7 的词错误率（WER）；在官方测试集上，该系统在槽填充任务中排名第 1（槽错误率 CoER 为 59.5），在 8 支参赛队伍的意图识别任务中排名第 4（准确率为 66.1%）。我们将公开实验脚本，并很快发布合成数据集以支持该领域的进一步研究。
英文摘要
We present Aslema, our system for NADI 2026 Shared Task 5, which consists of two subtasks: intent recognition and slot filling. We evaluate four omni LLMs in a zero-shot setting and compare them with fine-tuned models. Our results show that fine-tuning consistently outperforms zero-shot inference. We further explore synthetic data augmentation by using an LLM to generate culturally grounded Tunisian Derja utterances, followed by voice cloning to generate synthetic speech. Incorporating this synthetic data improves performance on both tasks. Our final submitted system, based on Qwen3-Omni-30B and trained with a mixture of original and synthetic data, achieves 86.8% intent accuracy and 34.7 WER on the devtest split. On the official test set it ranks 1st in slot filling (59.5 CoER) and 4th among 8 teams in intent recognition (66.1% accuracy). We release our experimental scripts and will soon share the synthetic dataset to support further research in this area.
CommentsLLMs, Native, Arabic LLMs, Augmentation, Multilingual, Multimodal, Language Diversity, Contextual Understanding, Minority Languages, Culturally Informed, Foundation Models, Large Language Models, Audio Models, Omni Models, Slot Filling
