构建首个覆盖5种亚洲语言的词汇规范化基准与生成模型。
MultiLexNorm++: A Unified Benchmark and a Generative Model for Lexical Normalization for Asian Languages
- 基于大模型设计统一生成架构，提升跨语言规范能力。
- 新基准显示旧模型在亚洲语言上性能下降超过15%。
- 适合多语言NLP研究者和社交文本处理开发者。
社交媒体数据因其信息丰富性长期受到自然语言处理研究者的关注，但其非正式、自发性强且存在多种社会方言的特点，导致现有NLP模型性能下降。为应对这一挑战，词汇规范化（lexical normalization）通过将非标准文本转换为标准形式来提升处理效果。尽管已有多个基准与模型被提出，但现有的MultiLexNorm基准几乎仅涵盖拉丁字母书写的印欧语系语言。为此，我们扩展了MultiLexNorm，新增涵盖5种来自不同语系、使用4种不同文字的亚洲语言。实验表明，此前的最先进模型在这些新语言上的表现显著下降。为此，我们提出一种基于大语言模型（LLMs）的新架构，在多种语言上展现出更强的鲁棒性。最后，我们分析了仍存在的错误模式，指明未来研究方向。
原文摘要 · Abstract (English)
Social media data has been of interest to Natural Language Processing (NLP) practitioners for over a decade, because of its richness in information, but also challenges for automatic processing. Since language use is more informal, spontaneous, and adheres to many different sociolects, the performance of NLP models often deteriorates. One solution to this problem is to transform data to a standard variant before processing it, which is also called lexical normalization. There has been a wide variety of benchmarks and models proposed for this task. The MultiLexNorm benchmark proposed to unify these efforts, but it consists almost solely of languages from the Indo-European language family in the Latin script. Hence, we propose an extension to MultiLexNorm, which covers 5 Asian languages from different language families in 4 different scripts. We show that the previous state-of-the-art model performs worse on the new languages and propose a new architecture based on Large Language Models (LLMs), which shows more robust performance. Finally, we analyze remaining errors, revealing future directions for this task.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。