用规则约束训练目标，让模型在少样本下也能精准标注词性与实体。
R2T: Rule-Encoded Loss Functions for Low-Resource Sequence Tagging
- 将语言规则融入损失函数，引导模型学习带不确定性的词汇处理机制。
- 仅用无标签文本训练的R2T-BiLSTM在扎尔马语词性标注上达98.2%准确率。
- 适用于低资源场景，50条标注数据即可超越传统300条训练效果。
我们提出规则转标注（R2T）框架，一种将多层级语言规则直接嵌入神经网络训练目标的混合方法。R2T的创新在于其自适应损失函数，包含一个正则化项，使模型能以合理不确定性处理未登录词（OOV）。本工作作为我们称之为严谨学习（PrL）范式的案例研究，即模型在显式任务约束下训练，而非仅依赖标注样本。我们在扎尔马语词性（POS）标注任务上的实验表明，仅使用无标签文本训练的R2T-BiLSTM模型达到98.2%准确率，优于在300个标注句子上微调的AfriBERTa基线。此外，对于更复杂的命名实体识别（NER）任务，R2T可作为强大预训练步骤：在仅50个标注句子上微调的模型，表现超过在300个句子上训练的基线。
原文摘要 · Abstract (English)
We introduce the Rule-to-Tag (R2T) framework, a hybrid approach that integrates a multi-tiered system of linguistic rules directly into a neural network's training objective. R2T's novelty lies in its adaptive loss function, which includes a regularization term that teaches the model to handle out-of-vocabulary (OOV) words with principled uncertainty. We frame this work as a case study in a paradigm we call principled learning (PrL), where models are trained with explicit task constraints rather than on labeled examples alone. Our experiments on Zarma part-of-speech (POS) tagging show that the R2T-BiLSTM model, trained only on unlabeled text, achieves 98.2% accuracy, outperforming baselines like AfriBERTa fine-tuned on 300 labeled sentences. We further show that for more complex tasks like named entity recognition (NER), R2T serves as a powerful pre-training step; a model pre-trained with R2T and fine-tuned on just 50 labeled sentences outperformes a baseline trained on 300.
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。