@inproceedings{sun-sobczak-2025-qm,
    title = "{QM}-{AI} at {S}em{E}val-2025 Task 6: an Ensemble of {BERT} Models for Promise Identification in {ESG} Context",
    author = "Sun, Zihang  and
      Sobczak, Filip",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/transition-to-people-yaml/2025.semeval-1.34/",
    pages = "228--233",
    ISBN = "979-8-89176-273-2",
    abstract = "This paper presents our approach and findings in the SemEval-2025 Task 6: Multinational, Multilingual, Multi-industry Promise Verification (PromiseEval), which focuses on verifying promises in the industrial Environmental, Social, and Governance (ESG) reports. Specifically, we participate in the first subtask of the PromiseEval shared task, promise identification. We tackle this subtask by building an ensemble of four BERT models trained in different experimental configurations, and deploying logistic regression as meta-model. Each configuration has a different combination of two variables: whether augmented data is used, and whether English translation is used. We find out that the BERT model trained without augmented data or English translation not only has the best evaluation results on the test data in most languages, but also has higher robustness than the meta-model. We submitted results from the meta-model to the leaderboard, and rank the first place in Japanese and Korean, the second place in French and Chinese, and the seventh place in English."
}