# To lemmatize or not to lemmatize: how word normalisation affects ELMo performance in word sense disambiguation

arXiv: https://arxiv.org/abs/1909.03135 · HTML: https://mlsanity.com/paper/1909.03135/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2019.

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

- [Linguistically inspired roadmap for building biologically reliable protein language models](https://mlsanity.com/paper/2207.00982/) (2022)
- [RoMe: A Robust Metric for Evaluating Natural Language Generation](https://mlsanity.com/paper/2203.09183/) (2022)
- [ImmunoLingo: Linguistics-based formalization of the antibody language](https://mlsanity.com/paper/2209.12635/) (2022)
- [Towards Resolving Word Ambiguity with Word Embeddings](https://mlsanity.com/paper/2307.13417/) (2023)

## Abstract (arXiv)

We critically evaluate the widespread assumption that deep learning NLP models do not require lemmatized input. To test this, we trained versions of contextualised word embedding ELMo models on raw tokenized corpora and on the corpora with word tokens replaced by their lemmas. Then, these models were evaluated on the word sense disambiguation task. This was done for the English and Russian languages. The experiments showed that while lemmatization is indeed not necessary for English, the situation is different for Russian. It seems that for rich-morphology languages, using lemmatized training and testing data yields small but consistent improvements: at least for word sense disambiguation. This means that the decisions about text pre-processing before training ELMo should consider the linguistic nature of the language in question.