测试时代码切换用于跨语言方面情感三元组抽取
Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction
AI总结：
针对跨语言ASTE任务，提出测试时代码切换框架TT-CSW，通过训练双语生成模型和测试时对齐增强，在四个数据集上平均F1提升3.7%，并超越ChatGPT和GPT-4。
摘要：
方面情感三元组抽取（ASTE）是一个蓬勃发展的研究领域，在高资源语言上取得了令人瞩目的成果。然而，跨语言迁移在ASTE任务中的应用相对未被探索，且现有的代码切换方法仍面临术语边界检测问题和词典外问题。在本研究中，我们提出了一种新颖的测试时代码切换（TT-CSW）框架，该框架弥合了双语训练阶段与单语测试时预测之间的差距。在训练阶段，我们基于双语代码切换训练数据开发了一个生成模型，该模型能够为双语输入生成双语ASTE三元组。在测试阶段，我们采用了一种基于对齐的代码切换技术进行测试时增强。在跨语言ASTE数据集上进行的大量实验验证了我们所提出方法的有效性。我们在四个不同语言的数据集上，在加权平均F1方面平均提升了3.7%。此外，我们使用ChatGPT和GPT-4设立了基准，并证明即使使用我们提出的TT-CSW框架微调的较小生成模型，也分别超越了ChatGPT和GPT-4达14.2%和5.0%。
英文摘要：
Aspect Sentiment Triplet Extraction (ASTE) is a thriving research area with impressive outcomes being achieved on high-resource languages. However, the application of cross-lingual transfer to the ASTE task has been relatively unexplored, and current code-switching methods still suffer from term boundary detection issues and out-of-dictionary problems. In this study, we introduce a novel Test-Time Code-SWitching (TT-CSW) framework, which bridges the gap between the bilingual training phase and the monolingual test-time prediction. During training, a generative model is developed based on bilingual code-switched training data and can produce bilingual ASTE triplets for bilingual inputs. In the testing stage, we employ an alignment-based code-switching technique for test-time augmentation. Extensive experiments on cross-lingual ASTE datasets validate the effectiveness of our proposed method. We achieve an average improvement of 3.7% in terms of weighted-averaged F1 in four datasets with different languages. Additionally, we set a benchmark using ChatGPT and GPT-4, and demonstrate that even smaller generative models fine-tuned with our proposed TT-CSW framework surpass ChatGPT and GPT-4 by 14.2% and 5.0% respectively.
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。
