改进多语言社交媒体洞察：基于方面的评论分析
Improving Multilingual Social Media Insights: Aspect-based Comment Analysis
AI总结：
针对社交媒体文本多样性带来的下游NLP任务挑战，提出基于方面术语生成（CAT-G）的多语言大模型微调方法，并贡献首个涵盖四种语言的多语言CAT-G测试集以评估跨语言性能。
摘要：
社交媒体帖子的固有特性，即语言使用自由且伴随着各种不同意见和主题的零散组合，对评论聚类、评论摘要和社交媒体意见分析等下游NLP任务构成了重大挑战。为了解决这一问题，我们提出了一种细粒度的方法，即从单个评论中识别并生成方面术语，以引导模型注意力。具体而言，我们利用多语言大语言模型并结合监督微调来进行评论方面术语生成（CAT-G），进一步通过DPO使模型的预测与人类期望保持一致。我们证明了该方法在两项NLP任务中提升社交媒体话语理解的有效性。此外，本文贡献了首个涵盖英语、中文、马来语和印尼语的多语言CAT-G测试集。由于LLM的能力在不同语言中存在差异，该测试集允许对具有不同LLM熟练度水平的语言进行性能比较分析。
英文摘要：
The inherent nature of social media posts, characterized by the freedom of language use with a disjointed array of diverse opinions and topics, poses significant challenges to downstream NLP tasks such as comment clustering, comment summarization, and social media opinion analysis. To address this, we propose a granular level of identifying and generating aspect terms from individual comments to guide model attention. Specifically, we leverage multilingual large language models with supervised fine-tuning for comment aspect term generation (CAT-G), further aligning the model's predictions with human expectations through DPO. We demonstrate the effectiveness of our method in enhancing the comprehension of social media discourse on two NLP tasks. Moreover, this paper contributes the first multilingual CAT-G test set on English, Chinese, Malay, and Bahasa Indonesian. As LLM capabilities vary among languages, this test set allows for a comparative analysis of performance across languages with varying levels of LLM proficiency.
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。
