Update README.md

README.md

@@ -42,84 +42,10 @@ fill_mask("Il [MASK] ha chiesto revocarsi l'obbligo di pagamento")
 # {'sequence': "Il lavoratore ha chiesto revocarsi l'obbligo di pagamento",'score': 0.028993653133511543},
 # {'sequence': "Il Ministero ha chiesto revocarsi l'obbligo di pagamento", 'score': 0.025297977030277252}]
 ```
-here how to use it for sentence similarity 
-```python
-from transformers import AutoTokenizer, AutoModel
-from sklearn.metrics.pairwise import cosine_similarity
-import torch
-import seaborn as sns
-import matplotlib.pyplot as plt
-from textwrap import wrap
-
-#Mean Pooling - Take attention mask into account for correct averaging
-def mean_pooling(model_output, attention_mask):
-    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
-    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
-    sum_embeddings = torch.sum(token_embeddings * input_mask_expanded, 1)
-    sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-9)
-    return sum_embeddings / sum_mask
-
-
-# gettting Sentence Embeddings
-def sentence_embeddings(sentences, model_name, max_length=512):
-    # load models
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    model = AutoModel.from_pretrained(model_name)
-    
-    #Tokenize sentences
-    encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=max_length, return_tensors='pt')
-
-    #Compute token embeddings
-    with torch.no_grad():
-        model_output = model(**encoded_input)
-
-    #Perform pooling. In this case, mean pooling
-    return mean_pooling(model_output, encoded_input['attention_mask']).detach().numpy()
 
+In this [COLAB ITALIAN-LEGAL-BERT : Minimal Start for Italian Legal Downstream Tasks](https://colab.research.google.com/drive/1aXOmqr70fjm8lYgIoGJMZDsK0QRIL4Lt?authuser=3#scrollTo=UgRBs1spJ-pG)
+ how to use it for sentence similarity, sentence classification and named entity recognition
 
-def plot_similarity(sentences, model_name):
-    # Get sentence embeddings produced by the model
-    embeddings = sentence_embeddings(sentences, model_name)
-    # Perfom similarity score using cosine similarity
-    corr = cosine_similarity(embeddings, embeddings)
-    
-    # Plot heatmap similarity
-    sns.set(font_scale=1.2)    
-    labels = [ '\n'.join(wrap(l, 40)) for l in sentences] # for text axis labels wrapping
-    g = sns.heatmap(
-      corr,
-      xticklabels=labels,
-      yticklabels=labels,
-      vmax=1,
-      cmap="YlOrRd")
-    g.set_xticklabels(labels, rotation=90)
-    model_short_name = model_name.split('/')[-1]
-    g.set_title(f"Semantic Textual Similarity ({model_short_name})")
-    plt.show()
-
-# Sentences to be compared    
-sent = [
-    # 1. "The court shall pronounce the judgment for the dissolution or termination of the civil effects of marriage."
-    "Il tribunale pronuncia la sentenza per lo scioglimento o la cessazione degli effetti civili del matrimonio",
-    
-    # 2. "having regard to Articles 1, 2, 3 No. 2(b) and 4 Paragraph 13 of Law No. 898 of December 1, 1970, as later amended."
-    # NOTE: Law Dec. 1, 1970 No. 898 is on divorce
-    "visti gli articoli 1, 2, 3 n. 2 lett. b) e 4 comma 13 della legge 1 dicembre 1970 n. 898 e successive modifiche",
-    
-    # 3. "The plaintiff has lost the case."
-    "Il ricorrente ha perso la causa"
-    ]
-
-# Perform Semantic Textual Similarity using 'Italian-Legal-BERT'
-model_name = "dlicari/Italian-Legal-BERT"
-plot_similarity(sent, model_name)
-
-# Perform Semantic Textual Similarity using 'bert-base-italian-xxl-cased'
-model_name =  'dbmdz/bert-base-italian-xxl-cased'
-plot_similarity(sent, model_name)
-```
-The similarity is shown in a heat map. The final graph is a 3x3 matrix in which each entry [i, j] is colored according to the cosine similarity of the encodings for sentences i and j
-<img  src="https://huggingface.co/dlicari/Italian-Legal-BERT/resolve/main/semantic_text_similarity.jpg" width="700"/> 
 
 <h2> Citation </h2>
 If you find our resource or paper is useful, please consider including the following citation in your paper.