@inproceedings{v-a-z-q-u-e-z-o-s-o-r-i-o-etal-2025-late,
    title = "{LATE}-{GIL}-{NLP} at {S}em{E}val-2025 Task 11: Multi-Language Emotion Detection and Intensity Classification Using Transformer Models with Optimized Loss Functions for Imbalanced Data",
    author = "V {\'a} z q u e z - O s o r i o, Jes{\'u}s  and
      G{\'o}mez - Adorno, Helena  and
      Sierra, Gerardo  and
      Sierra - Casiano, Vladimir  and
      Canchola - Hern{\'a}ndez, Diana  and
      Tovar - Cort{\'e}s, Jos{\'e}  and
      Sol{\'i}s - Vilchis, Roberto  and
      Salazar, Gabriel",
    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/corrections-2025-08/2025.semeval-1.93/",
    pages = "666--674",
    ISBN = "979-8-89176-273-2",
    abstract = "This paper addresses our approach to Task 11 (Track A and B) at the SemEval-2025, which focuses on the challenge of multilingual emotion detection in text, specifically identifying perceived emotions. The task is divided into tracks, we participated in two tracks: Track A, involving multilabel emotion detection, and Track B, which extends this to predicting emotion intensity on an ordinal scale. Addressing the challenges of imbalanced data and linguistic diversity, we propose a robust approach using pre-trained language models, fine-tuned with techniques such as extensive and deep hyperparameter optimization, along with loss function combinations to improve performance on imbalanced datasets and underrepresented languages. Our results demonstrate strong performance on Track A, particularly in low-resource languages such as Tigrinya (ranked 2nd), Igbo (ranked 3rd), and Oromo (ranked 4th). This work offers a scalable framework for emotion detection with applications in cross-cultural communication and human-computer interaction."
}