metadata

language:
  - sk
tags:
  - text-classification
  - pytorch
metrics:
  - accuracy
  - f1-score
extra_gated_prompt: >-
  Our models are intended for academic use only. If you are not affiliated with
  an academic institution, please provide a rationale for using our models.

  If you use our models for your work or research, please cite this paper:
  Sebők, M., Máté, Á., Ring, O., Kovács, V., & Lehoczki, R. (2024). Leveraging
  Open Large Language Models for Multilingual Policy Topic Classification: The
  Babel Machine Approach. Social Science Computer Review, 0(0).
  https://doi.org/10.1177/08944393241259434
extra_gated_fields:
  Name: text
  Country: country
  Institution: text
  E-mail: text
  Use case: text

xlm-roberta-large-slovak-cap-v3

Model description

An xlm-roberta-large model fine-tuned on slovak training data labeled with major topic codes from the Comparative Agendas Project.

How to use the model

from transformers import AutoTokenizer, pipeline

tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-large")
pipe = pipeline(
    model="poltextlab/xlm-roberta-large-slovak-cap-v3",
    task="text-classification",
    tokenizer=tokenizer,
    use_fast=False,
    token="<your_hf_read_only_token>"
)

text = "We will place an immediate 6-month halt on the finance driven closure of beds and wards, and set up an independent audit of needs and facilities."
pipe(text)

Gated access

Due to the gated access, you must pass the token parameter when loading the model. In earlier versions of the Transformers package, you may need to use the use_auth_token parameter instead.

Model performance

The model was evaluated on a test set of 321525 examples.
Model accuracy is 0.81.

label	precision	recall	f1-score	support
0	0.78	0.73	0.75	21169
1	0.66	0.66	0.66	7640
2	0.86	0.87	0.86	15711
3	0.82	0.83	0.82	8727
4	0.71	0.72	0.72	9208
5	0.87	0.86	0.86	13629
6	0.83	0.77	0.8	7593
7	0.82	0.82	0.82	6633
8	0.78	0.73	0.75	2841
9	0.86	0.85	0.85	11411
10	0.82	0.79	0.8	18679
11	0.75	0.77	0.76	8788
12	0.74	0.72	0.73	6301
13	0.77	0.75	0.76	15354
14	0.81	0.79	0.8	15575
15	0.82	0.77	0.8	5398
16	0.8	0.79	0.8	5995
17	0.71	0.72	0.72	18052
18	0.74	0.78	0.76	34200
19	0.82	0.85	0.84	12586
20	0.57	0.71	0.63	6499
21	0.94	0.94	0.94	69536
macro avg	0.79	0.78	0.78	321525
weighted avg	0.81	0.81	0.81	321525

Fine-tuning procedure

This model was fine-tuned with the following key hyperparameters:

Number of Training Epochs: 10
Batch Size: 50
Learning Rate: 5e-06
Early Stopping: enabled with a patience of 2 epochs

Inference platform

This model is used by the CAP Babel Machine, an open-source and free natural language processing tool, designed to simplify and speed up projects for comparative research.

Cooperation

Model performance can be significantly improved by extending our training sets. We appreciate every submission of CAP-coded corpora (of any domain and language) at poltextlab{at}poltextlab{dot}com or by using the CAP Babel Machine.

Reference

Sebők, M., Máté, Á., Ring, O., Kovács, V., & Lehoczki, R. (2024). Leveraging Open Large Language Models for Multilingual Policy Topic Classification: The Babel Machine Approach. Social Science Computer Review, 0(0). https://doi.org/10.1177/08944393241259434

Debugging and issues

This architecture uses the sentencepiece tokenizer. In order to use the model before transformers==4.27 you need to install it manually.

If you encounter a RuntimeError when loading the model using the from_pretrained() method, adding ignore_mismatched_sizes=True should solve the issue.