xlm-roberta-large-ineq-binary-v6

Model desicription

An xlm-roberta-large model finetuned on english-translated, sentence-segmented parliamentary speeches training data from the V4 countries (Czechia, Hungary, Poland, and SLovakia). The model uses the following codebook:

Label	Description
(0) Not inequality related	If the text in question does not relate to individual-level economic inequality
(1) Inequality related	If the text in question relates to individual-level economic inequality

How to use the model

from transformers import AutoTokenizer, pipeline

tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-large")
pipe = pipeline(
    model="poltextlab/xlm-roberta-large-ineq-binary-v6",
    task="text-classification",
    tokenizer=tokenizer,
    use_fast=False,
    token="<your_hf_read_only_token>"
)

text = "<text_to_classify>"
pipe(text)

Classification Report

Overall Performance:

• Accuracy: N/A
• Macro Avg: Precision: 0.82, Recall: 0.82, F1-score: 0.82
• Weighted Avg: Precision: 0.82, Recall: 0.82, F1-score: 0.82

Per-Class Metrics:

Label	Precision	Recall	F1-score	Support
(0) Not inequality related	0.82	0.82	0.82	51
(1) Inequality related	0.82	0.82	0.82	51

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.

Debugging and issues

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