tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: >-
Kremlissä sihteeristö on kiireellä kirjoitellut ”da” lappuja, jotka
toimittaa perille Nopea Kortteliohjuspalvelu Byroo (NKB). Aika kätevästi
Venäjä ”äänestää” itselleen puolustettavaa aluetta.
- text: Etunimi Sukunimi tai Keisarillista Venäjää johon Suomi kuului.
- text: Etunimi Sukunimi 🙋♀️
- text: >-
No jos haluaa lapsensa kotiin jättää, niin luultavasti se lupa joko lomaan
tai kotiopetukseen tulee koululta. Oman lapsen kohdalla riitti rehtorille
ilmoitus ja kaikki oli kunnossa ettei nuori tule kouluun. Tehtävät tulee
kotiin, niin kuin esim. lomalle jäädessä.
metrics:
- metric
pipeline_tag: text-classification
library_name: setfit
inference: true
base_model: TurkuNLP/bert-base-finnish-cased-v1
model-index:
- name: SetFit with TurkuNLP/bert-base-finnish-cased-v1
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: metric
value: 0.9149516574585634
name: Metric
Detect Actions in Asynchronous Conversation Comments
SetFit with TurkuNLP/bert-base-finnish-cased-v1
This is a SetFit model that can be used for Text Classification of actions in asynchronous conversation. This particular model detects if a comment includes a request or not. The configuration of the model is that the model is based on averaged annotations (from 3 annotators). Metric evaluations are based on conservative ground truth (see paper). This SetFit model uses TurkuNLP/bert-base-finnish-cased-v1 as the Sentence Transformer embedding model (using word embeddings). A LogisticRegression instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
- Fine-tuning a Sentence Transformer with contrastive learning.
- Training a classification head with features from the fine-tuned Sentence Transformer.
Model Details
Model Description
- Model Type: SetFit
- Sentence Transformer body: TurkuNLP/bert-base-finnish-cased-v1
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 512 tokens
- Number of Classes: 2 classes
Model Sources
- Repository: GitHub
- Paper: Paakki, H., Toivanen, P. and Kajava K. (2025). Implicit and Indirect: Detecting Face-threatening and Paired Actions in Asynchronous Online Conversations. Northern European Journal of Language Technology (NEJLT), 11(1), pp. 58-83.
Model Labels
| Label | Examples |
|---|---|
| 0 |
|
| 1 |
|
Evaluation
Metrics
| Label | Metric |
|---|---|
| 10-fold cross-validated F1 | 0.74 |
Uses
Direct Use for Inference
First install the SetFit library:
pip install setfit
Then you can load this model and run inference.
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("Finnish-actions/SetFit-FinBERT1-Avg-request")
# Run inference
preds = model("Etunimi Sukunimi 🙋♀️")
Downstream Use
NB. This model has been trained on data coming from Finnish language asynchronous conversations under crisis related news on Facebook. This specific model has been trained to detect whether a comment includes a question or not. It reflects only one of our annotators' label interpretations, so the best use of our models (see our paper) would be to combine a set of models we provide on our Huggingface (Finnish-actions), and use a model ensemble to provide label predictions. It needs to be noted also that the model may not be well applicable outside of its empirical context, so in downstream applications, one should always conduct an evaluation of the model applicability using manually annotated data from that specific context (see our paper for annotation instructions).
Out-of-Scope Use
Please use this model only for action detection and analysis. Uses of this model and the involved data for generative purposes (e.g. NLG) is prohibited.
Bias, Risks and Limitations
Note that the model may produce errors. Due to the size of the training dataset, model may not generalize very well even for other novel topics within the same context. Note that model predictions should not be regarded as final judgments e.g. for online moderation purposes, but each case should also be regarded individually if using model predictions to support moderation. Also, the annotations only reflect three (though experienced) annotators' interpretations, so there might be perspectives on data intepretation that have not been taken into account here. If model is used to support moderation on social media, we recommend that final judgments should always be left for human moderators.
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 1 | 20.3800 | 213 |
| Label | Training Sample Count |
|---|---|
| 0 | 758 |
| 1 | 84 |
Framework Versions
- Python: 3.11.9
- SetFit: 1.1.3
- Sentence Transformers: 3.2.0
- Transformers: 4.44.0
- PyTorch: 2.4.0+cu124
- Datasets: 2.21.0
- Tokenizers: 0.19.1
Citation
BibTeX
@article{paakki-implicit-indirect,
doi = {https://doi.org/10.3384/nejlt.2000-1533.2025.5980},
url = {https://nejlt.ep.liu.se/article/view/5980},
author = {Paakki, Henna and Toivanen, Pihla and Kajava, Kaisla},
title = {Implicit and Indirect: Detecting Face-threatening and Paired Actions in Asynchronous Online Conversations},
publisher = {Northern European Journal of Language Technology (NEJLT)},
volume= {11},
number= {1},
year = {2025}
}