Update README.md

README.md

@@ -5,10 +5,16 @@ tags:
 - sentence-transformers
 - text-classification
 pipeline_tag: text-classification
+language:
+- fr
+metrics:
+- f1
 ---
 
 # binbin83/setfit-MiniLM-dialog-themes-13-nov
 
+The model is a multi-class multi-label text classifier to distinguish the  different dialog act in semi-structured interview. The data used fot fine-tuning were in French.
+
 This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text 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.
@@ -29,12 +35,53 @@ from setfit import SetFitModel
 
 # Download from Hub and run inference
 model = SetFitModel.from_pretrained("binbin83/setfit-MiniLM-dialog-themes-13-nov")
+label_dict = {'CauseConsequences': 0, 'PersonalExperience': 1, 'Connaissance': 2, 'Other': 3, 'Reconstitution': 4, 'Temps': 5, 'Reaction': 6, 'Nouvelle': 7, 'Media': 8, 'Lieux': 9}
 # Run inference
-preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
+preds = model(["Vous pouvez continuer", "Pouvez-vous me dire précisément quel a été l'odre chronologique des événements ?"])
+labels = [[[f for f, p in zip(labels_dict, ps) if p] for ps in [pred]] for pred in preds ]
+
 ```
 
+##  Labels and training data
+Based on interview guide, the themes evocated in the interview where : 
+
+['CauseConsequences', 'PersonalExperience', 'Connaissance', 'Other', 'Reconstitution', 'Temps', 'Reaction', 'Nouvelle', 'Media', 'Lieux']
+
+We label a small amount of data: 
+('Other', 50), ('Reaction', 46), ('PersonalExperience', 41), ('CauseConsequences', 41), ('Media', 27), ('Lieux', 13), ('Nouvelle', 10), ('Temps', 9), ('Reconstitution', 7), ('Connaissance', 3)
+
+and finetune a set fit model on it
+
+
+## Training and Performances
+
+We finetune: "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
+using SetFit with CosineLossSimilarity and this parapeters: epochs = 10, batch_size=32, num_iterations = 20
+
+
+
+On our test dataset, we get this results: 
+{'f1': 0.639, 'f1_micro': 0.6808510638297872, 'f1_sample': 0.6666666666666666, 'accuracy': 0.6086956521739131}
+
 ## BibTeX entry and citation info
 
+
+To cite the current study:
+```bibtex
+@article{
+doi = {conference paper},
+url = {https://arxiv.org/abs/2209.11055},
+author = {Quillivic Robin, Charles Payet},
+keywords = {NLP, JADT},
+title = {Semi-Structured Interview Analysis: A French NLP Toolbox for Social Sciences},
+publisher = {JADT},
+year = {2024},
+copyright = {Creative Commons Attribution 4.0 International}
+}
+```
+
+
+To cite the setFit paper: 
 ```bibtex
 @article{https://doi.org/10.48550/arxiv.2209.11055,
 doi = {10.48550/ARXIV.2209.11055},
@@ -46,4 +93,4 @@ publisher = {arXiv},
 year = {2022},
 copyright = {Creative Commons Attribution 4.0 International}
 }
-```
+```