翻译与融合提升零样本跨语言信息抽取
Translation and Fusion Improves Zero-shot Cross-lingual Information Extraction
AI总结：
针对大语言模型在低资源语言信息抽取中表现受限的问题，提出TransFusion翻译融合框架及跨语言指令微调模型GoLLIE-TF，在多语言数据集上实现更优零样本跨语言迁移，且适配多种模型架构均能提升低资源语言命名实体识别性能。
摘要：
大语言模型（LLM）结合指令微调已在信息抽取（IE）任务中取得显著进展，能够遵循标注规范对未见过的数据集展现出强泛化能力。然而，由于缺乏用于微调的标注数据以及用于预训练的无标注文本，这类模型在低资源语言中的适用性仍然有限。本文提出TransFusion（翻译融合）框架，在该框架中模型经过微调后可使用低资源语言数据的英文译本，并通过标注融合实现更精准的预测。基于TransFusion，我们推出GoLLIE-TF，这是一款面向信息抽取任务的跨语言指令微调大语言模型，旨在缩小高资源与低资源语言之间的性能差距。我们在涵盖50种语言的12个多语言信息抽取数据集上开展实验，结果表明GoLLIE-TF相比基础模型实现了更优的零样本跨语言迁移效果。此外，我们还证明，当通过提示工程应用于GPT-4等专有模型时，TransFusion可将低资源语言命名实体识别性能提升5个F1值；而在对包括仅解码器架构（提升14个F1值）和仅编码器架构（提升13个F1值）在内的不同语言模型进行微调时，该框架同样能显著提升低资源语言命名实体识别效果。
英文摘要：
Large language models (LLMs) combined with instruction tuning have shown significant progress in information extraction (IE) tasks, exhibiting strong generalization capabilities to unseen datasets by following annotation guidelines. However, their applicability to low-resource languages remains limited due to lack of both labeled data for fine-tuning, and unlabeled text for pre-training. In this paper, we propose TransFusion, a framework in which models are fine-tuned to use English translations of low-resource language data, enabling more precise predictions through annotation fusion. Based on TransFusion, we introduce GoLLIE-TF, a cross-lingual instruction-tuned LLM for IE tasks, designed to close the performance gap between high and low-resource languages. Our experiments across twelve multilingual IE datasets spanning 50 languages demonstrate that GoLLIE-TF achieves better zero-shot cross-lingual transfer over the base model. In addition, we show that TransFusion significantly improves low-resource language named entity recognition when applied to proprietary models such as GPT-4 (+5 F1) with a prompting approach, or fine-tuning different language models including decoder-only (+14 F1) and encoder-only (+13 F1) architectures.
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。
