基于语言类型学的候选重排序用于基于大语言模型的低资源语言翻译
Typologically-Informed Candidate Reranking for LLM-based Translation into Low-Resource Languages
AI总结：
本文提出一种基于语言类型学的候选重排序框架，通过语言类型学分析提升低资源语言翻译质量，无需平行数据或模型重训练。
摘要：
训练主要基于高资源语言的大型语言模型表现出系统性的偏向于主导语言类型模式的偏差，导致在翻译到语言类型学上差异显著的低资源语言时出现结构不一致。我们提出了一种框架，利用语言类型学来提高翻译质量，而无需平行训练数据或模型重新训练。该框架包含两个组成部分：通用元语言框架（UMF），它通过16个语言类型学维度上的结构化配置文件来表示语言，并采用权重差异评分；以及计算引擎，它在生成过程中通过语言歧义消解，在选择过程中通过语言类型学符合评分进行操作。在九个语言对上的评估显示干预率与英语的语言类型学距离呈强相关。在341个英语句子的实验中，每个句子具有不同的形态学和句法现象，该框架在保守处理语言上的干预精度为48.16%，在形态学密集语言上的干预精度为28.15%，在结构配置语言上的干预精度为86.26%。该框架不需要平行训练数据，且可以使用任何能够生成多个候选输出的LLM进行操作，使在资源匮乏语言上的实际部署成为可能。
英文摘要：
Large language models trained predominantly on high-resource languages exhibit systematic biases toward dominant typological patterns, leading to structural non-conformance when translating into typologically divergent low-resource languages. We present a framework that leverages linguistic typology to improve translation quality without parallel training data or model retraining. The framework consists of two components: the Universal Metalinguistic Framework (UMF), which represents languages as structured profiles across 16 typological dimensions with divergence-weighted scoring, and the Computational Engine, which operates through linguistic disambiguation during generation and typological compliance scoring during selection. Evaluation across nine language pairs demonstrates intervention rates strongly correlating with typological distance from English. In experiments on 341 English sentences each having different morphological and syntactic phenomena, the framework shows an intervention precision of 48.16% for conservatively treated languages, 28.15% for morphologically dense languages, and 86.26% for structurally profiled languages. The framework requires no parallel training data and operates with any LLM capable of producing multiple candidate outputs, enabling practical deployment for under-resourced languages.
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。
