# MoNoise: Modeling Noise Using a Modular Normalization System

arXiv: https://arxiv.org/abs/1710.03476 · HTML: https://mlsanity.com/paper/1710.03476/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2017.

## Built on by (most cited first, 8 of 8)

- [Improving Formality Style Transfer with Context-Aware Rule Injection](https://mlsanity.com/paper/2106.00210/) (2021)
- [Sequence-to-Sequence Lexical Normalization with Multilingual Transformers](https://mlsanity.com/paper/2110.02869/) (2021)
- [BLUE at Memotion 2.0 2022: You have my Image, my Text and my Transformer](https://mlsanity.com/paper/2202.07543/) (2022)
- [Script Normalization for Unconventional Writing of Under-Resourced Languages in Bilingual Communities](https://mlsanity.com/paper/2305.16407/) (2023)
- [MANorm: A Normalization Dictionary for Moroccan Arabic Dialect Written in Latin Script](https://mlsanity.com/paper/2206.09167/) (2022)
- [A categorical error sensitivity index (ISEC): A preventive ordinal decision-support measure for irrecoverable errors in manual data entry systems](https://mlsanity.com/paper/2605.12328/) (2026)
- [The Curse of Multilinguality in Lexical Normalization](https://mlsanity.com/paper/2609.00329/) (2026)
- [Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts](https://mlsanity.com/paper/2609.00330/) (2026)

## Abstract (arXiv)

We propose MoNoise: a normalization model focused on generalizability and efficiency, it aims at being easily reusable and adaptable. Normalization is the task of translating texts from a non- canonical domain to a more canonical domain, in our case: from social media data to standard language. Our proposed model is based on a modular candidate generation in which each module is responsible for a different type of normalization action. The most important generation modules are a spelling correction system and a word embeddings module. Depending on the definition of the normalization task, a static lookup list can be crucial for performance. We train a random forest classifier to rank the candidates, which generalizes well to all different types of normaliza- tion actions. Most features for the ranking originate from the generation modules; besides these features, N-gram features prove to be an important source of information. We show that MoNoise beats the state-of-the-art on different normalization benchmarks for English and Dutch, which all define the task of normalization slightly different.