Abstract
Interlinear glossed text (IGT) creation remains a major bottleneck in linguistic documentation and fieldwork, particularly for low-resource morphologically rich languages. We present a hybrid automatic glossing pipeline that combines neural sequence labeling with large language model (LLM) post-correction, evaluated on Jungar Tuvan, a low-resource Turkic language. Through systematic ablation studies, we show that retrieval-augmented prompting provides substantial gains over random example selection. We further find that morpheme dictionaries paradoxically hurt performance compared to providing no dictionary at all in most cases, and that performance scales approximately logarithmically with the number of few-shot examples. Most significantly, our two-stage pipeline combining a BiLSTM-CRF model with LLM post-correction yields substantial gains for most models, achieving meaningful reductions in annotation workload. Drawing on these findings, we establish concrete design principles for integrating structured prediction models with LLM reasoning in morphologically complex fieldwork contexts. These principles demonstrate that hybrid architectures offer a promising direction for computationally light solutions to automatic linguistic annotation in endangered language documentation.
Abstract (translated)
交叉线注释文本（IGT）的创建仍然是语言记录和实地研究中的一个主要瓶颈，尤其是在资源较少、形态丰富的语言中。我们提出了一种结合神经序列标注与大型语言模型（LLM）后校正的混合自动注解管道，并在一种低资源突厥语——楚瓦什图瓦尼语上对其进行了评估。通过系统的消融研究，我们发现检索增强提示比随机示例选择提供了显著的优势。此外，我们发现在大多数情况下，形态词典反而会损害性能，相比于不提供任何字典的情况。同时，我们还发现性能随着少量样本数量的增加近似对数增长。 最重要的是，我们的两阶段管道将BiLSTM-CRF模型与LLM后校正结合使用，在大多数模型中产生了显著的效果提升，实现了注释工作量的实质性减少。基于这些发现，我们在形态复杂的实地研究环境中建立了结构化预测模型和LLM推理集成的具体设计原则。这些原则表明，混合架构为濒危语言文档自动语言注解提供了有希望的方向，并且可以实现计算负担较轻的解决方案。
URL
https://arxiv.org/abs/2603.00923
