Update README.md

README.md

@@ -40,11 +40,11 @@ model-index:
       value: 0.8718253349471188
       name: Metric
 ---
+# Detect Questions in Asynchronous Conversation Comments
 
-# SetFit with TurkuNLP/bert-base-finnish-cased-v1
-
-This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [TurkuNLP/bert-base-finnish-cased-v1](https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
+## SetFit with TurkuNLP/bert-base-finnish-cased-v1
 
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification of actions in asynchronous conversation. This particular model detects if a comment includes a question or not. The configuration of the model is that the model is based on only one annotator's annotations (annotator A3). 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. A LogisticRegression instance is used for classification.
 The model has been trained using an efficient few-shot learning technique that involves:
 
 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
@@ -57,21 +57,21 @@ The model has been trained using an efficient few-shot learning technique that i
 - **Sentence Transformer body:** [TurkuNLP/bert-base-finnish-cased-v1](https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1)
 - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
 - **Maximum Sequence Length:** 512 tokens
-- **Number of Classes:** 2 classes
+- **Number of Classes:** 2 classes (contains statement - yes or no)
 <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
 <!-- - **Language:** Unknown -->
 <!-- - **License:** Unknown -->
 
 ### Model Sources
 
-- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
-- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
-- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
+- **Repository:** [GitHub](https://github.com/henniina/Detecting-paired-actions)
+- **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                                                                                                                                                                                                                                                                                                                                                                                                                                   |
 |:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| 1     | <ul><li>'Etunimi Raines jep. Suomalainen rokottamaton paha, ukrainalainen rokottamaton hyvä. Tää näkyy olevan nyt se mentaliteetti tällä hetkellä...'</li><li>'Etunimi Bistrom tilastot.'</li><li>'Etunimi Sukunimi myös delta oli suurimmalle osalle myös rokottamattomille lähes oireeton, omikron kuulemma vielä lievempi👏'</li></ul>                                                                                                   |
+| 1     | <ul><li>'Etunimi Sukunimi jep. Suomalainen rokottamaton paha, ukrainalainen rokottamaton hyvä. Tää näkyy olevan nyt se mentaliteetti tällä hetkellä...'</li><li>'Etunimi Sukunimi tilastot.'</li><li>'Etunimi Sukunimi myös delta oli suurimmalle osalle myös rokottamattomille lähes oireeton, omikron kuulemma vielä lievempi👏'</li></ul>                                                                                                   |
 | 0     | <ul><li>'Etunimi Sukunimi RAutaa rajoille Suomi suureksi ja Viena vapaaksi'</li><li>'Perussuomalaiset siivoamassa keskustelupalstoja, koronakriisiavustuksien avulla? Onhan tämä nyt joku Monty Python -sketsi?'</li><li>'on se hyvä että Kiurussa ei ole miestä vaan Niskavuoren Hetaa joka pistää tuollaisen pojanklopin aisoihin viimeistään silloin kun Vapaavuori on kaltereissa johtaessaan Uuttamaata terveyspaniikkiin.'</li></ul> |
 
 ## Evaluation
@@ -79,7 +79,7 @@ The model has been trained using an efficient few-shot learning technique that i
 ### Metrics
 | Label   | Metric |
 |:--------|:-------|
-| **all** | 0.8718 |
+| **5-fold cross-validated F1** | 0.78 |
 
 ## Uses
 
@@ -102,23 +102,22 @@ model = SetFitModel.from_pretrained("Finnish-actions/SetFit-FinBERT1-A3")
 preds = model("Etunimi Sukunimi ei varmasti moni uskalla")
 ```
 
-<!--
+
 ### Downstream Use
 
-*List how someone could finetune this model on their own dataset.*
--->
+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
 
-*List how the model may foreseeably be misused and address what users ought not to do with the model.*
--->
+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
 
-*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
--->
+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.
+
 
 <!--
 ### Recommendations
@@ -138,6 +137,7 @@ preds = model("Etunimi Sukunimi ei varmasti moni uskalla")
 | 0     | 263                   |
 | 1     | 700                   |
 
+<!--
 ### Training Hyperparameters
 - batch_size: (16, 16)
 - num_epochs: (4, 4)
@@ -223,6 +223,7 @@ preds = model("Etunimi Sukunimi ei varmasti moni uskalla")
 | 3.8728 | 2800 | 0.0019        | -               |
 | 3.9419 | 2850 | 0.0025        | -               |
 | 4.0    | 2892 | -             | 0.2222          |
+-->
 
 ### Framework Versions
 - Python: 3.11.9
@@ -237,16 +238,17 @@ preds = model("Etunimi Sukunimi ei varmasti moni uskalla")
 
 ### BibTeX
 ```bibtex
-@article{https://doi.org/10.48550/arxiv.2209.11055,
-    doi = {10.48550/ARXIV.2209.11055},
-    url = {https://arxiv.org/abs/2209.11055},
-    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
-    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
-    title = {Efficient Few-Shot Learning Without Prompts},
-    publisher = {arXiv},
-    year = {2022},
-    copyright = {Creative Commons Attribution 4.0 International}
+@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}
 }
+
 ```
 
 <!--