license: cc-by-4.0
language:
- multilingual
tags:
- text-classification
- pytorch
metrics:
- f1-score
extra_gated_fields:
Country: country
Institution: text
Institution Email: text
Full Name: text
Please specify your academic project/use case you want to use the models for: text
extra_gated_prompt: >-
Our models are intended for academic projects and academic research only. If
you are not affiliated with an academic institution, please reach out to us at
huggingface [at] poltextlab [dot] com for further inquiry. If we cannot
clearly determine your academic affiliation and use case based on your form
data, your request may be rejected. Please allow us a few business days to
manually review subscriptions.
xlm-roberta-large-pooled-MORES
Model description
An xlm-roberta-large model finetuned on sentence-level multilingual training data hand-annotated using the following labels:
- 0: "Anger"
- 1: "Fear"
- 2: "Disgust"
- 3: "Sadness"
- 4: "Joy"
- 5: "None of Them"
This model can also be used for sentiment classification with the following conversion:
- Joy (4) → Positive
- None of Them (5) → Neutral (or None of Them)
- All Other Labels → Negative
The training data we used was augmented using artificially generated examples and translated texts. It covers 7 languages (English, German, French, Polish, Slovak, Czech and Hungarian) with nearly identical shares.
How to use the model
from transformers import AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-large")
pipe = pipeline(
model="poltextlab/xlm-roberta-large-pooled-MORES",
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 language-specific test sets and demonstrated nearly identical performance across all languages:
Fine-tuning procedure
This model was fine-tuned with the following key hyperparameters:
- Number of Training Epochs: 10
- Batch Size: 16
- Learning Rate: 5e-06
- Early Stopping: enabled with a patience of 2 epochs
Inference platform
This model is used by the 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 coded corpora (of any domain and language) at poltextlab{at}poltextlab{dot}com or by using the Babel Machine.
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.
Funding
The research was funded by European Union’s Horizon 2020 research and innovation program, “MORES” project (Grant No.: 101132601).