@inproceedings{sharma-2026-edunlp,
    title = "{E}du{NLP} at {BEA} 2026 Shared Task 1: Multi-Model Ensemble with Feature-Augmented Transformers for Vocabulary Difficulty Prediction",
    author = "Sharma, Avinash Kumar",
    editor = "Kochmar, Ekaterina  and
      Alhafni, Bashar  and
      Bann{\`o}, Stefano  and
      Bexte, Marie  and
      Burstein, Jill  and
      Horbach, Andrea  and
      Laarmann-Quante, Ronja  and
      Tack, Anais  and
      Yaneva, Victoria  and
      Yuan, Zheng",
    booktitle = "Proceedings of the 21st Workshop on Innovative Use of {NLP} for Building Educational Applications ({BEA} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bea-1.71/",
    pages = "1024--1028",
    ISBN = "979-8-89176-409-5",
    abstract = "We describe our system submitted to the BEA 2026 Shared Task on Vocabulary Difficulty Prediction for English Learners. Our approach combines handcrafted linguistic features with fine-tuned XLM-RoBERTa transformers in a multi-model ensemble, participating in both the closed and open tracks. Our system outperforms the baselines on both tracks across all three L1s, with best RMSEs of 1.058 (closed, CN) and 0.992 (open, CN). Post-hoc error analysis reveals that polysemous words in rare senses and nominalized -ing forms constitute the primary failure mode."
}