The pre-trained huBERT was fine-tuned on the Hunglish 2.0 parallel corpus to mimic the bert-base-nli-stsb-mean-tokens model provided by UKPLab. Sentence embeddings were obtained by applying mean pooling to the huBERT output. The data was split into training (98%) and validation (2%) sets. By the end of the training, a mean squared error of 0.106 was computed on the validation set. Our code was based on the Sentence-Transformers library. Our model was trained for 2 epochs on a single GTX 1080Ti GPU card with the batch size set to 32. The training took approximately 15 hours.

If you use this model, please cite the following paper:

@article {bertopic,
    title = {Analyzing Narratives of Patient Experiences: A BERT Topic Modeling Approach},
    journal = {Acta Polytechnica Hungarica},
    year = {2023},
    author = {Osváth, Mátyás and Yang, Zijian Győző and Kósa, Karolina},
    pages = {153--171},
    volume = {20},
    number = {7}
}