Budget-Xfer: 为非洲语言的跨语言迁移进行预算约束的源语言选择
Budget-Xfer: Budget-Constrained Source Language Selection for Cross-Lingual Transfer to African Languages
AI总结：
本文提出Budget-Xfer框架，通过预算约束资源分配问题优化多源跨语言迁移，验证多源迁移在命名实体识别和情感分析中的优越性，揭示嵌入相似性在不同任务中的表现差异。
摘要：
跨语言迁移学习通过利用高资源语言的标注数据使低资源语言的NLP成为可能，但现有源语言选择策略比较未控制总训练数据量，导致语言选择效应与数据量效应混淆。我们引入Budget-Xfer框架，将多源跨语言迁移视为预算约束的资源分配问题。给定固定注释预算B，我们的框架联合优化应包含哪些源语言以及从每个源语言分配多少数据。我们评估了四种分配策略，针对三种非洲目标语言（豪萨语、约鲁巴语、斯瓦希里语）的命名实体识别和情感分析任务，使用两种多语言模型进行了288次实验。我们的结果表明：（1）多源迁移显著优于单源迁移（Cohen's d = 0.80至1.98），驱动因素是结构性预算利用瓶颈；（2）在多源策略中，差异较小且非显著；（3）嵌入相似性作为选择代理的价值取决于任务，随机选择在命名实体识别中优于相似性基于的选择，但在情感分析中不显著。
英文摘要：
Cross-lingual transfer learning enables NLP for low-resource languages by leveraging labeled data from higher-resource sources, yet existing comparisons of source language selection strategies do not control for total training data, confounding language selection effects with data quantity effects. We introduce Budget-Xfer, a framework that formulates multi-source cross-lingual transfer as a budget-constrained resource allocation problem. Given a fixed annotation budget B, our framework jointly optimizes which source languages to include and how much data to allocate from each. We evaluate four allocation strategies across named entity recognition and sentiment analysis for three African target languages (Hausa, Yoruba, Swahili) using two multilingual models, conducting 288 experiments. Our results show that (1) multi-source transfer significantly outperforms single-source transfer (Cohen's d = 0.80 to 1.98), driven by a structural budget underutilization bottleneck; (2) among multi-source strategies, differences are modest and non-significant; and (3) the value of embedding similarity as a selection proxy is task-dependent, with random selection outperforming similarity-based selection for NER but not sentiment analysis.
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。
