# MultiLexNorm++: A Unified Benchmark and a Generative Model for Lexical Normalization for Asian Languages

arXiv: https://arxiv.org/abs/2601.16623 · HTML: https://mlsanity.com/paper/2601.16623/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 70 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Builds on (most cited first, 25 of 25)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [BERTweet: A pre-trained language model for English Tweets](https://mlsanity.com/paper/2005.10200/) (2020)
- [XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond](https://mlsanity.com/paper/2104.12250/) (2021)
- [Multi-VALUE: A Framework for Cross-Dialectal English NLP](https://mlsanity.com/paper/2212.08011/) (2022)
- [Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP](https://mlsanity.com/paper/2005.14672/) (2020)
- [What to do about non-standard (or non-canonical) language in NLP](https://mlsanity.com/paper/1608.07836/) (2016)
- [Self-Attention with Cross-Lingual Position Representation](https://mlsanity.com/paper/2004.13310/) (2020)
- [Parsing Tweets into Universal Dependencies](https://mlsanity.com/paper/1804.08228/) (2018)
- [DaN+: Danish Nested Named Entities and Lexical Normalization](https://mlsanity.com/paper/2105.11301/) (2021)
- [Universal Dependency Parsing for Hindi-English Code-switching](https://mlsanity.com/paper/1804.05868/) (2018)
- [Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation](https://mlsanity.com/paper/2302.14220/) (2023)
- [Adapting Sequence to Sequence models for Text Normalization in Social Media](https://mlsanity.com/paper/1904.06100/) (2019)
- [Understanding Model Robustness to User-generated Noisy Texts](https://mlsanity.com/paper/2110.07428/) (2021)
- [Lexical Normalization for Code-switched Data and its Effect on POS-tagging](https://mlsanity.com/paper/2006.01175/) (2020)
- [Sequence-to-Sequence Lexical Normalization with Multilingual Transformers](https://mlsanity.com/paper/2110.02869/) (2021)
- ['UFAL at MultiLexNorm 2021: Improving Multilingual Lexical Normalization by Fine-tuning ByT5](https://mlsanity.com/paper/2110.15248/) (2021)
- [Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling](https://mlsanity.com/paper/2211.12781/) (2022)
- [We're Calling an Intervention: Exploring Fundamental Hurdles in Adapting Language Models to Nonstandard Text](https://mlsanity.com/paper/2404.07304/) (2024)
- [Exploring Robustness of Multilingual LLMs on Real-World Noisy Data](https://mlsanity.com/paper/2501.08322/) (2025)
- [Understanding the Impact of UGC Specificities on Translation Quality](https://mlsanity.com/paper/2110.12551/) (2021)
- [Sentiment Analysis of German Twitter](https://mlsanity.com/paper/1911.13062/) (2019)

## Built on by (most cited first, 1 of 1)

- [Phonemizing User-Generated Text: A Benchmark, Taxonomy, and Compositional Approach](https://mlsanity.com/paper/2609.27205/) (2026)

## Abstract (arXiv)

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.