@inproceedings{nguyen-etal-2018-introducing,
    title = "Introducing Two {V}ietnamese Datasets for Evaluating Semantic Models of (Dis-)Similarity and Relatedness",
    author = "Nguyen, Kim Anh  and
      Schulte im Walde, Sabine  and
      Vu, Ngoc Thang",
    editor = "Walker, Marilyn  and
      Ji, Heng  and
      Stent, Amanda",
    booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)",
    month = jun,
    year = "2018",
    address = "New Orleans, Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/N18-2032/",
    doi = "10.18653/v1/N18-2032",
    pages = "199--205",
    abstract = "We present two novel datasets for the low-resource language Vietnamese to assess models of semantic similarity: ViCon comprises pairs of synonyms and antonyms across word classes, thus offering data to distinguish between similarity and dissimilarity. ViSim-400 provides degrees of similarity across five semantic relations, as rated by human judges. The two datasets are verified through standard co-occurrence and neural network models, showing results comparable to the respective English datasets."
}