Hungarian Aspect-based Sentiment Analysis with finetuned XLM-RoBERTa model

For further models, scripts and details, see our repository or our demo site.

Pretrained model used: XLM-RoBERTa
Finetuned on OpinHuBank (OHB) Corpus
Labels: 0 (negative), 2 (neutral), 3 (positive)
Separator: </s>

Limitations

max_seq_length = 256

Results

Model	OHB
huBERT	82.30
XLM-R	80.59

Usage with pipeline

from transformers import pipeline

classification = pipeline(task="sentiment-analysis", model="NYTK/sentiment-ohb3-xlm-roberta-hungarian")
input_text = "Kovácsné Nagy Erzsébet </s> A Kovácsné Nagy Erzsébet nagyon jól érzi magát a Nokiánál, azonban a Németországból érkezett Kovács Péter nehezen boldogul a beilleszkedéssel."

print(classification(input_text)[0])

Citation

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

@article {laki-yang-sentiment,
      author = {Laki, László János and Yang, Zijian Győző},
      title = {Sentiment Analysis with Neural Models for Hungarian},
      journal = {Acta Polytechnica Hungarica},
      year = {2023},
      publisher = {Obuda University},
      volume = {20},
      number = {5},
      doi = {10.12700/APH.20.5.2023.5.8},
      pages=      {109--128},
      url = {https://acta.uni-obuda.hu/Laki_Yang_134.pdf}
}

@inproceedings {yang-asent,
    title = {Neurális entitásorientált szentimentelemző alkalmazás magyar nyelvre},
    booktitle = {XIX. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY 2023)},
    year = {2023},
    publisher = {Szegedi Tudományegyetem, Informatikai Intézet},
    address = {Szeged, Hungary},
    author = {Yang, Zijian Győző and Laki, László János},
    pages = {107--117}
}