# Strong Baselines for Complex Word Identification across Multiple Languages

arXiv: https://arxiv.org/abs/1904.05953 · HTML: https://mlsanity.com/paper/1904.05953/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2019.

## Built on by (most cited first, 9 of 9)

- [Predicting Lexical Complexity in English Texts: The Complex 2.0 Dataset](https://mlsanity.com/paper/2102.08773/) (2021)
- [UPB at SemEval-2021 Task 1: Combining Deep Learning and Hand-Crafted Features for Lexical Complexity Prediction](https://mlsanity.com/paper/2104.06983/) (2021)
- [Domain Adaptation in Multilingual and Multi-Domain Monolingual Settings for Complex Word Identification](https://mlsanity.com/paper/2205.07283/) (2022)
- [Lexical Complexity Prediction: An Overview](https://mlsanity.com/paper/2303.04851/) (2023)
- [Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain Setups](https://mlsanity.com/paper/2411.01706/) (2024)
- [Multilingual Lexical Simplification via Paraphrase Generation](https://mlsanity.com/paper/2307.15286/) (2023)
- [A User-Centered Evaluation of Spanish Text Simplification](https://mlsanity.com/paper/2308.07556/) (2023)
- [Society of Medical Simplifiers](https://mlsanity.com/paper/2410.09631/) (2024)
- [What makes a word hard to learn? Modeling L1 influence on English vocabulary difficulty](https://mlsanity.com/paper/2605.12281/) (2026)

## Abstract (arXiv)

Complex Word Identification (CWI) is the task of identifying which words or phrases in a sentence are difficult to understand by a target audience. The latest CWI Shared Task released data for two settings: monolingual (i.e. train and test in the same language) and cross-lingual (i.e. test in a language not seen during training). The best monolingual models relied on language-dependent features, which do not generalise in the cross-lingual setting, while the best cross-lingual model used neural networks with multi-task learning. In this paper, we present monolingual and cross-lingual CWI models that perform as well as (or better than) most models submitted to the latest CWI Shared Task. We show that carefully selected features and simple learning models can achieve state-of-the-art performance, and result in strong baselines for future development in this area. Finally, we discuss how inconsistencies in the annotation of the data can explain some of the results obtained.