# To Normalize, or Not to Normalize: The Impact of Normalization on Part-of-Speech Tagging

arXiv: https://arxiv.org/abs/1707.05116 · HTML: https://mlsanity.com/paper/1707.05116/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2017.

## Built on by (most cited first, 4 of 4)

- [Lemmatization of Historical Old Literary Finnish Texts in Modern Orthography](https://mlsanity.com/paper/2107.03266/) (2021)
- [Annotating Norwegian Language Varieties on Twitter for Part-of-Speech](https://mlsanity.com/paper/2210.06150/) (2022)
- [Investigating Semi-Supervised Learning Algorithms in Text Datasets](https://mlsanity.com/paper/2401.01843/) (2024)
- [Not All Duplicates Are Coordination: Generic vs. Non-Generic Duplicate Campaigns in Information Operations](https://mlsanity.com/paper/2609.13671/) (2026)

## Abstract (arXiv)

Does normalization help Part-of-Speech (POS) tagging accuracy on noisy, non-canonical data? To the best of our knowledge, little is known on the actual impact of normalization in a real-world scenario, where gold error detection is not available. We investigate the effect of automatic normalization on POS tagging of tweets. We also compare normalization to strategies that leverage large amounts of unlabeled data kept in its raw form. Our results show that normalization helps, but does not add consistently beyond just word embedding layer initialization. The latter approach yields a tagging model that is competitive with a Twitter state-of-the-art tagger.