MultiLexNorm++: A Unified Benchmark and a Generative Model for Lexical Normalization for Asian Languages
This work addresses the problem of NLP performance degradation on informal social media text for Asian languages, but it is incremental as it builds upon existing benchmarks and methods.
The authors tackled the lack of lexical normalization benchmarks for Asian languages by extending the MultiLexNorm benchmark to include 5 Asian languages across 4 scripts, and proposed a new LLM-based architecture that shows more robust performance, though specific numerical gains are not detailed.
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.