分布偏移下的零样本跨语言情感分类：一项探索性研究
Zero-Shot Cross-Lingual Sentiment Classification under Distribution Shift: an Exploratory Study
AI总结：
本研究探索零样本跨语言情感分类中语言与领域偏移对OOD泛化的影响，验证反事实增强数据在低资源语言中的有效性，并提出两种利用大语言模型的低成本新方法，在部分数据集上达到与CAD相当或更高的准确率。
摘要：
微调语言模型在未见领域中的分布外（OOD）测试样本上性能的脆弱性已在英语环境中得到充分研究，但在多语言模型中尚未被探索。因此，我们专门在零样本跨语言迁移设置中研究对OOD测试数据的泛化能力，分析训练与测试数据之间语言和领域偏移对性能的影响。我们进一步评估反事实增强数据（CAD）在跨语言环境中改善OOD泛化的有效性，因为CAD已被证明在单语英语环境中有效。最后，我们提出了两种新的OOD泛化方法，通过利用近期大型语言模型（LLMs）的能力，避免与CAD相关的昂贵标注过程。我们使用3个多语言模型（LaBSE、mBERT和XLM-R）在英语IMDb电影评论上进行训练，并在13种语言的OOD测试集上评估：亚马逊产品评论、推文和餐厅评论。结果印证了在单语英语环境中观察到的OOD性能下降。此外，（i）来自原始高资源语言的反事实确实改善了低资源语言中的OOD泛化，（ii）我们新提出的成本效益方法在亚马逊和餐厅评论上达到了与CAD相似或高达+3.1%更好的准确率。
英文摘要：
The brittleness of finetuned language model performance on out-of-distribution (OOD) test samples in unseen domains has been well-studied for English, yet is unexplored for multi-lingual models. Therefore, we study generalization to OOD test data specifically in zero-shot cross-lingual transfer settings, analyzing performance impacts of both language and domain shifts between train and test data. We further assess the effectiveness of counterfactually augmented data (CAD) in improving OOD generalization for the cross-lingual setting, since CAD has been shown to benefit in a monolingual English setting. Finally, we propose two new approaches for OOD generalization that avoid the costly annotation process associated with CAD, by exploiting the power of recent large language models (LLMs). We experiment with 3 multilingual models, LaBSE, mBERT, and XLM-R trained on English IMDb movie reviews, and evaluate on OOD test sets in 13 languages: Amazon product reviews, Tweets, and Restaurant reviews. Results echo the OOD performance decline observed in the monolingual English setting. Further, (i) counterfactuals from the original high-resource language do improve OOD generalization in the low-resource language, and (ii) our newly proposed cost-effective approaches reach similar or up to +3.1% better accuracy than CAD for Amazon and Restaurant reviews.
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。
