面向跨语言结构化预测的上下文标签投影
Contextual Label Projection for Cross-Lingual Structured Prediction
AI总结：
针对现有跨语言标签投影方法准确率不足的问题，提出以译文为上下文的CLaP标签投影方法，借助多语言指令微调模型实现，在39种语言的两项结构化预测任务上取得显著F1提升，且在极低资源语言中具备应用潜力。
摘要：
标签投影（即同步获取翻译后的标签与文本）对利用机器翻译助力结构化预测任务中的跨语言迁移至关重要。以往探索标签投影的研究往往因偏向简化的标签翻译或仅依赖词级对齐，而牺牲了翻译准确率。本文提出一种新型标签投影方法CLaP（上下文标签投影）：先将文本翻译为目标语言，再以翻译后的文本为上下文对标签进行上下文翻译，从而提升标签翻译的准确率。我们采用具备多语言能力的指令微调语言模型作为上下文翻译器，通过指令约束翻译后的标签必须出现在译文中。我们在事件论元抽取（EAE）和命名实体识别（NER）这两项代表性结构化预测任务上，针对39种语言的零样本跨语言迁移场景，将CLaP与其他标签投影技术进行基准测试，结果显示CLaP在EAE任务上F1值提升超2.4，在NER任务上F1值提升1.4。我们进一步探究了CLaP在十种极低资源语言上的适用性，以展现其在跨语言结构化预测领域的潜力。
英文摘要：
Label projection, which involves obtaining translated labels and texts jointly, is essential for leveraging machine translation to facilitate cross-lingual transfer in structured prediction tasks. Prior research exploring label projection often compromise translation accuracy by favoring simplified label translation or relying solely on word-level alignments. In this paper, we introduce a novel label projection approach, CLaP, which translates text to the target language and performs contextual translation on the labels using the translated text as the context, ensuring better accuracy for the translated labels. We leverage instruction-tuned language models with multilingual capabilities as our contextual translator, imposing the constraint of the presence of translated labels in the translated text via instructions. We benchmark CLaP with other label projection techniques on zero-shot cross-lingual transfer across 39 languages on two representative structured prediction tasks - event argument extraction (EAE) and named entity recognition (NER), showing over 2.4 F1 improvement for EAE and 1.4 F1 improvement for NER. We further explore the applicability of CLaP on ten extremely low-resource languages to showcase its potential for cross-lingual structured prediction.
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。
