Cross-Lingual Approaches for Text Difficulty Classification in Non-English Languages

Huili Dai

Abstract


Text Difficulty Classification (TDC) significantly contributes to educational technology, language learning, and information access by automatically predicting the difficulty of texts. While English has been favored with extensive resources and mature readability tools, non-English languages suffer from sparse annotated corpora, linguistic diversity, and insufficient computational resources. Cross-lingual methods, including shared knowledge transfer from high-resource to low-resource languages, have become increasingly popular in recent years. It covers the latest advances in cross-lingual TDC in pipelines of machine translation-based, multi-lingual pre-trained transformers (e.g., mBERT, XLM-R), adversarial and meta-learning-based approaches, and knowledge distillation techniques. It also summarizes available datasets and benchmarks, critiques current practices, and highlights morphological complexity, translation artifacts, and domain mismatch. It identifies significant trends and future promise by critically examining state-of-the-art methods for multimodal TDC, hybrid architectures, and active learning in low-resource languages. The results highlight the significance of non-discriminatory, resource-lean systems for measuring fair-minded text difficulty in many languages.

Full Text:

PDF

References


Balyan, R., McCarthy, K. S., & McNamara, D. S. (2020). Applying natural language processing and hierarchical machine learning approaches to text difficulty classification. International Journal of Artificial Intelligence in Education, 30(3), 337–370. https://doi.org/10.1007/s40593-020-00201-7

Schwarm, S. E., & Ostendorf, M. (2005). Reading level assessment using support vector machines and statistical language models. Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), 523–530. https://doi.org/10.3115/1219840.1219905

Heilman, M., Collins-Thompson, K., & Eskenazi, M. (2008). An analysis of statistical models and features for reading difficulty prediction. Proceedings of the Third Workshop on Innovative Use of NLP for Building Educational Applications, 71–79.

De Clercq, O., & Hoste, V. (2016). All mixed up? Finding the optimal feature set for general readability prediction and its application to English and Dutch. Computational Linguistics, 42(3), 457–490. https://doi.org/10.1162/COLI_a_00255

Aluisio, S., Specia, L., Gasperin, C., & Scarton, C. (2010). Readability assessment for text simplification. Proceedings of the NAACL HLT 2010 Fifth Workshop on Innovative Use of NLP for Building Educational Applications, 1–9.

Vajjala, S., & Meurers, D. (2012). On improving the accuracy of readability classification using insights from second language acquisition. Proceedings of the Seventh Workshop on Building Educational Applications Using NLP, 163–173.

Sinha, M., Dasgupta, T., & Basu, A. (2014). Text readability in Hindi: A comparative study of feature performances using support vectors. Proceedings of the 11th International Conference on Natural Language Processing, 223–231.

Madrazo Azpiazu, I., & Pera, M. S. (2020). Is cross-lingual readability assessment possible? Journal of the Association for Information Science and Technology, 71(6), 644–656. https://doi.org/10.1002/asi.24293

Weiss, Z., Chen, X., & Meurers, D. (2021). Using broad linguistic complexity modeling for cross-lingual readability assessment. Proceedings of the 10th Workshop on NLP for Computer Assisted Language Learning, 38–54.

Khallaf, N., & Sharoff, S. (2021). Automatic difficulty classification of Arabic sentences. https://doi.org/10.48550/arXiv.2103.04386

Li, W., Wang, Z., & Wu, Y. (2022). A unified neural network model for readability assessment with feature projection and length-balanced loss. https://doi.org/10.48550/arXiv.2210.10305

Mohtaj, S., Naderi, B., Möller, S., Maschhur, F., Wu, C., & Reinhard, M. (2022). A transfer learning based model for text readability assessment in German. https://doi.org/10.48550/arXiv.2207.06265

Ivanov, V. V. (2022). Sentence-level complexity in Russian: An evaluation of BERT and graph neural networks. Frontiers in Artificial Intelligence, 5, 1008411. https://doi.org/10.3389/frai.2022.1008411

Varnamkhasti, M. M. (2024). Persian readability classification using DeepWalk and tree-based ensemble methods. Natural Language Processing Journal, 9, 100116. https://doi.org/10.1016/j.nlp.2024.100116

Van Ngo, D., & Parmentier, Y. (2023). Towards sentence-level text readability assessment for French. Second Workshop on Text Simplification, Accessibility and Readability (TSAR@RANLP2023).

Pickelmann, F., Färber, M., & Jatowt, A. (2023). Ablesbarkeitsmesser: A system for assessing the readability of German text. European Conference on Information Retrieval, 288–293. https://doi.org/10.1007/978-3-031-28241-6_28

Leal, S. E., Duran, M. S., Scarton, C. E., Hartmann, N. S., & Aluísio, S. M. (2024). NILC-Metrix: Assessing the complexity of written and spoken language in Brazilian Portuguese. Language Resources and Evaluation, 58(1), 73–110. https://doi.org/10.1007/s10579-023-09693-w

Ribeiro, E., Mamede, N., & Baptista, J. (2024). Text readability assessment in European Portuguese: A comparison of classification and regression approaches. Proceedings of the 16th International Conference on Computational Processing of Portuguese, 551–557.

Naous, T., Ryan, M. J., Lavrouk, A., Chandra, M., & Xu, W. (2023). ReadMe++: Benchmarking multilingual language models for multi-domain readability assessment. https://doi.org/10.48550/arXiv.2305.14463

Naderi, B., Mohtaj, S., Ensikat, K., & Möller, S. (2019). Subjective assessment of text complexity: A dataset for German language. https://doi.org/10.48550/arXiv.1904.07733

Lu, D., Qiu, X., & Cai, Y. (2020). Sentence-level readability assessment for L2 Chinese learning. In Chinese Lexical Semantics: 20th Workshop, CLSW 2019, Revised Selected Papers 20, 381–392. https://doi.org/10.1007/978-3-030-38189-9_40

Yang, S., Sun, R., & Wan, X. (2023). A new dataset and empirical study for sentence simplification in Chinese. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 8306–8321. https://doi.org/10.48550/arXiv.2306.04188

Mohammadi, H., & Khasteh, S. H. (2020). A machine learning approach to Persian text readability assessment using a crowdsourced dataset. 2020 28th Iranian Conference on Electrical Engineering (ICEE), 1–7. https://doi.org/10.1109/ICEE50131.2020.9260933

Martinez, A. R. (2012). Part-of-speech tagging. Wiley Interdisciplinary Reviews: Computational Statistics, 4(1), 107–113. https://doi.org/10.1002/wics.195

Hamilton, W. L. (2020). Graph representation learning. Morgan & Claypool Publishers. https://doi.org/10.2200/S01045ED1V01Y202009AIM046

Grover, A., & Leskovec, J. (2016). node2vec: Scalable feature learning for networks. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 855–864. https://doi.org/10.1145/2939672.2939754

Cunningham, P., & Delany, S. J. (2021). K-nearest neighbour classifiers—a tutorial. ACM Computing Surveys, 54(6), 1–25. https://doi.org/10.1145/3459665

Kramer, O. (2013). K-nearest neighbors. In Dimensionality Reduction with Unsupervised Nearest Neighbors (pp. 13–23). Springer. https://doi.org/10.1007/978-3-642-38652-7_2

Yao, L., Mao, C., & Luo, Y. (2019). Graph convolutional networks for text classification. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 7370–7377. https://doi.org/10.1609/aaai.v33i01.33017370




DOI: https://doi.org/10.31449/inf.v46i21.8968

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.