通过噪声注入与层组合，提升挪威方言意图槽位识别性能
Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detection
- 在模型中注入字符级噪声，增强对方言的鲁棒性
- 混合英语与少量方言数据训练，实现85.6%槽位F1和97.6%意图准确率
- 层交换技术有效整合多源模型，适合低资源方言任务
槽位与意图检测（SID）是经典的自然语言理解任务。尽管如此，针对方言和口语变体的研究仍处于起步阶段。许多适用于低资源场景的方法尚未应用于方言SID数据，或未在相同数据集上进行比较。我们参与了VarDial 2025关于挪威方言槽位与意图检测的共享任务，对比多种设置：训练数据（英语、标准挪威语或方言挪威语）、注入字符级噪声、训练辅助任务，以及应用层交换（Layer Swapping）——将不同数据集微调的模型层组合成新模型。结果表明，噪声注入有益，而辅助任务效果参差不齐。尽管组装模型需一定调试，但表现令人惊喜；结合英语与少量方言数据训练的模型，在槽位预测上最为稳健。最佳模型在共享任务中达到97.6%的意图准确率和85.6%的槽位F1值。
原文摘要 · Abstract (English)
Slot and intent detection (SID) is a classic natural language understanding task. Despite this, research has only more recently begun focusing on SID for dialectal and colloquial varieties. Many approaches for low-resource scenarios have not yet been applied to dialectal SID data, or compared to each other on the same datasets. We participate in the VarDial 2025 shared task on slot and intent detection in Norwegian varieties, and compare multiple set-ups: varying the training data (English, Norwegian, or dialectal Norwegian), injecting character-level noise, training on auxiliary tasks, and applying Layer Swapping, a technique in which layers of models fine-tuned on different datasets are assembled into a model. We find noise injection to be beneficial while the effects of auxiliary tasks are mixed. Though some experimentation was required to successfully assemble a model from layers, it worked surprisingly well; a combination of models trained on English and small amounts of dialectal data produced the most robust slot predictions. Our best models achieve 97.6% intent accuracy and 85.6% slot F1 in the shared task.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。