metadata

language: hr
tags:
  - text-classification
  - sentiment-analysis
widget:
  - text: >-
      Potpredsjednik Vlade i ministar branitelja Tomo Medved komentirao je
      Vladine planove za zakonsku zabranu pozdrava 'za dom spremni'.

bcms-bertic-parlasent-bcs-ter

Text classification model based on classla/bcms-bertic and fine-tuned on the BCS Political Sentiment dataset.

Fine-tuning hyperparameters

Fine-tuning was performed with simpletransformers. Beforehand a brief sweep for the optimal number of epochs was performed and the presumed best value was 9.


model_args = {
        "num_train_epochs": 9
        }

Performance

The same pipeline was run with two other transformer models and fasttext for comparison. Macro F1 scores were recorded for each of the 6 fine-tuning sessions and post festum analyzed.

model	average macro F1
bcms-bertic-parlasent-bcs-ter	0.7941 ±0.0101 **
EMBEDDIA/crosloengual-bert	0.7709 ± 0.0113
xlm-roberta-base	0.7184 ± 0.0139
fasttext + CLARIN.si embeddings	0.6312 ± 0.0043

Two best performing models have been compared with the Mann-Whitney U test. (** denotes $p<0.01$).

Citation

If you use the model, please cite the following paper on which the original model is based:

@inproceedings{ljubesic-lauc-2021-bertic,
    title = "{BERT}i{\'c} - The Transformer Language Model for {B}osnian, {C}roatian, {M}ontenegrin and {S}erbian",
    author = "Ljube{\v{s}}i{\'c}, Nikola  and Lauc, Davor",
    booktitle = "Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing",
    month = apr,
    year = "2021",
    address = "Kiyv, Ukraine",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2021.bsnlp-1.5",
    pages = "37--42",
}