README extended

README.md

@@ -10,8 +10,8 @@ tags:
 ## Abstract
 
 Sentiment analysis is a common task to understand people's reactions online. Still, we often need more nuanced information: is the post negative because the user is angry or because they are sad?
-An abundance of approaches has been introduced for tackling both tasks. However, at least for Italian, they all treat only one of the tasks at a time. We introduce FEEL-IT, a novel benchmark corpus of Italian Twitter posts annotated with four basic emotions: anger, fear, joy, sadness. By collapsing them, we can also do sentiment analysis. We evaluate our corpus on benchmark datasets for both emotion and sentiment classification, obtaining competitive results.
-We release an open-source Python library, so researchers can use a model trained on FEEL-IT for inferring both sentiments and emotions from Italian text.
+An abundance of approaches has been introduced for tackling both tasks. However, at least for Italian, they all treat only one of the tasks at a time. We introduce *FEEL-IT*, a novel benchmark corpus of Italian Twitter posts annotated with four basic emotions: **anger, fear, joy, sadness**. By collapsing them, we can also do **sentiment analysis**. We evaluate our corpus on benchmark datasets for both emotion and sentiment classification, obtaining competitive results.
+We release an [open-source Python library](https://github.com/MilaNLProc/feel-it), so researchers can use a model trained on FEEL-IT for inferring both sentiments and emotions from Italian text.
 
 | Model                       | Download |
 | ------                      | -------------------------|
@@ -21,15 +21,18 @@ We release an open-source Python library, so researchers can use a model trained
 
 ## Model
 
-The feel-it-italian-sentiment model performs sentiment analysis. We fine-tuned the [UmBERTo model](https://huggingface.co/Musixmatch/umberto-commoncrawl-cased-v1) on our new dataset (i.e., FEEL-IT) obtaining state-of-the-art performances on different data sets.
+The *feel-it-italian-sentiment* model performs **sentiment analysis** on Italian. We fine-tuned the [UmBERTo model](https://huggingface.co/Musixmatch/umberto-commoncrawl-cased-v1) on our new dataset (i.e., FEEL-IT) obtaining state-of-the-art performances on different benchmark corpus.
 
 ## Data
 
-Our data has been collected by annotating tweets from a broad range of topics. In total, we have 2037 tweets annotated with an emotion label. More details can be found in our paper.
+Our data has been collected by annotating tweets from a broad range of topics. In total, we have 2037 tweets annotated with an emotion label. More details can be found in our paper (preprint available soon).
 
 ## Performance
 
-We evaluate our performance using [SENTIPOLC16 Evalita](http://www.di.unito.it/~tutreeb/sentipolc-evalita16/data.html). This dataset comes with a training set and a testing set and thus we can compare the performance of different training datasets on the SENTIPOLC test set We collapsed the FEEL-IT classes into 2 by mapping joy to the positive class and anger, fear and sadness into the negative class. 
+We evaluate our performance using [SENTIPOLC16 Evalita](http://www.di.unito.it/~tutreeb/sentipolc-evalita16/). We collapsed the FEEL-IT classes into 2 by mapping joy to the *positive* class and anger, fear and sadness into the *negative* class. We compare three different training dataset combinations to understand whether it is better to train on FEEL-IT, SP16, or both by testing on the SP16 test set.
+
+
+This dataset comes with a training set and a testing set and thus we can compare the performance of different training datasets on the SENTIPOLC test set. 
 
 We use the fine-tuned UmBERTo model. The results show that FEEL-IT can provide better results on the SENTIPOLC test set than those that can be obtained with the SENTIPOLC training set. 
 
@@ -42,10 +45,29 @@ We use the fine-tuned UmBERTo model. The results show that FEEL-IT can provide b
 ## Usage
 
 ```python
+import torch
+import numpy as np 
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
+# Load model and tokenizer
 tokenizer = AutoTokenizer.from_pretrained("MilaNLProc/feel-it-italian-sentiment")
 model = AutoModelForSequenceClassification.from_pretrained("MilaNLProc/feel-it-italian-sentiment")
+
+sentence = 'Oggi sono proprio contento!'
+inputs = tokenizer(sentence, return_tensors="pt")
+
+# Call the model and get the logits
+labels = torch.tensor([1]).unsqueeze(0)  # Batch size 1
+outputs = model(**inputs, labels=labels)
+loss, logits = outputs[:2]
+logits = logits.squeeze(0)
+
+# Extract probabilities
+proba = torch.nn.functional.softmax(logits, dim=0)
+
+# Unpack the tensor to obtain negative and positive probabilities
+negative, positive = proba
+print(f"Probabilities: Negative {np.round(negative.item(),4)} - Positive {np.round(positive.item(),4)}")
 ```
 
 ## Citation