利用 LLM 和受约束解码推进序列到序列模型的跨语言基于方面的情感分析
Advancing Cross-lingual Aspect-Based Sentiment Analysis with LLMs and Constrained Decoding for Sequence-to-Sequence Models
AI总结:
提出一种基于受约束解码的序列到序列方法,解决跨语言复合 ABSA 任务中对外部翻译工具的依赖,性能提升达 10%,并验证了微调多语言 LLMs 的有效性。
摘要:
基于方面的情感分析(ABSA)已取得显著进展,但由于主要关注英语,低资源语言仍面临挑战。当前的跨语言 ABSA 研究通常集中于较简单的任务,并严重依赖外部翻译工具。在本文中,我们提出了一种用于复合 ABSA 任务的新型序列到序列方法,消除了对此类工具的需求。我们的方法使用受约束解码,将跨语言 ABSA 性能提升了高达 10%。该方法拓宽了跨语言 ABSA 的范围,使其能够处理更复杂的任务,并为依赖翻译的技术提供了实用、高效的替代方案。此外,我们将该方法与大型语言模型(LLMs)进行了比较,结果表明,虽然微调的多语言 LLMs 能取得可比的结果,但以英语为中心的 LLMs 在这些任务上表现不佳。
英文摘要:
Aspect-based sentiment analysis (ABSA) has made significant strides, yet challenges remain for low-resource languages due to the predominant focus on English. Current cross-lingual ABSA studies often centre on simpler tasks and rely heavily on external translation tools. In this paper, we present a novel sequence-to-sequence method for compound ABSA tasks that eliminates the need for such tools. Our approach, which uses constrained decoding, improves cross-lingual ABSA performance by up to 10\%. This method broadens the scope of cross-lingual ABSA, enabling it to handle more complex tasks and providing a practical, efficient alternative to translation-dependent techniques. Furthermore, we compare our approach with large language models (LLMs) and show that while fine-tuned multilingual LLMs can achieve comparable results, English-centric LLMs struggle with these tasks.
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。