arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.18895cs.CL
收藏

我们能否教会语言模型为濒危语言做词间注译?

Can we teach language models to gloss endangered languages?

University of Colorado(科罗拉多大学);New College of Florida(佛罗里达新学院)

Michael Ginn, Mans Hulden, Alexis Palmer

AI总结:

本研究探索大语言模型通过上下文学习自动生成濒危语言词间注译文本(IGT)的可行性,提出针对性的上下文示例选择方法以提升性能,证实无训练的LLM方法优于标准Transformer基线,实用性强。

摘要:

词间注译文本(Interlinear glossed text,IGT)是语言记录项目中常用的格式,每个语素都会被标注描述性注解。实现词间注译文本的自动化生成十分必要,可减少标注人员工作量并保持标注语料库的一致性。已有研究探索了多种统计方法与神经方法来自动生成IGT。\n鉴于大语言模型(Large Language Models,LLMs)在多语言任务中展现出良好效果,甚至对稀有濒危语言也适用,人们自然会好奇它们能否用于生成IGT的任务。我们探究了LLMs无需传统训练、仅通过上下文学习完成词间注译任务的有效性。我们提出了多种选择上下文示例的新方法,发现针对性选择能显著提升性能。研究结果表明,基于LLM的方法无需任何训练,性能仍优于标准Transformer基线模型。这些方法的表现虽仍不及该任务当前最优的监督系统,但对NLP领域之外的研究者而言实用性极强,使用成本极低。

英文摘要:

Interlinear glossed text (IGT) is a popular format in language documentation projects, where each morpheme is labeled with a descriptive annotation. Automating the creation of interlinear glossed text would be desirable to reduce annotator effort and maintain consistency across annotated corpora. Prior research has explored a number of statistical and neural methods for automatically producing IGT. As large language models (LLMs) have showed promising results across multilingual tasks, even for rare, endangered languages, it is natural to wonder whether they can be utilized for the task of generating IGT. We explore whether LLMs can be effective at the task of interlinear glossing with in-context learning, without any traditional training. We propose new approaches for selecting examples to provide in-context, observing that targeted selection can significantly improve performance. We find that LLM-based methods beat standard transformer baselines, despite requiring no training at all. These approaches still underperform state-of-the-art supervised systems for the task, but are highly practical for researchers outside of the NLP community, requiring minimal effort to use.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑