@inproceedings{qiu-etal-2024-complex,
    title = "{C}omp{L}ex-{ZH}: A New Dataset for Lexical Complexity Prediction in {M}andarin and {C}antonese",
    author = "Qiu, Le  and
      Guo, Shanyue  and
      Wong, Tak-Sum  and
      Chersoni, Emmanuele  and
      Lee, John  and
      Huang, Chu-Ren",
    editor = "Shardlow, Matthew  and
      Saggion, Horacio  and
      Alva-Manchego, Fernando  and
      Zampieri, Marcos  and
      North, Kai  and
      {\v{S}}tajner, Sanja  and
      Stodden, Regina",
    booktitle = "Proceedings of the Third Workshop on Text Simplification, Accessibility and Readability (TSAR 2024)",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.tsar-1.3/",
    doi = "10.18653/v1/2024.tsar-1.3",
    pages = "20--26",
    abstract = "The prediction of lexical complexity in context is assuming an increasing relevance in Natural Language Processing research, since identifying complex words is often the first step of text simplification pipelines. To the best of our knowledge, though, datasets annotated with complex words are available only for English and for a limited number of Western languages.In our paper, we introduce CompLex-ZH, a dataset including words annotated with complexity scores in sentential contexts for Chinese. Our data include sentences in Mandarin and Cantonese, which were selected from a variety of sources and textual genres. We provide a first evaluation with baselines combining hand-crafted and language models-based features."
}