Update README.md

README.md

@@ -41,4 +41,77 @@ fill_mask("Il [MASK] ha chiesto revocarsi l'obbligo di pagamento")
 # {'sequence': "Il resistente ha chiesto revocarsi l'obbligo di pagamento",'score': 0.039877112954854965},
 # {'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
+import seaborn as sns
+import matplotlib.pyplot as pl
+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()
+
+
+def plot_similarity(sentences, model_name):
+    # get sentence embeddings produced by the model
+    embeddings = sentence_embeddings(sentences, model_name)
+    # perfome similarity score using cosine similarity
+    corr = cosine_similarity(embeddings, embeddings)
+    
+    # plot heatmap similarity
+    sns.set(font_scale=1.2)
+    # for text axis labels wrapping
+    labels = [ '\n'.join(wrap(l, 40)) for l in sentences]
+    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()
+
+    
+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"
+    ]
+
+
+model_name = "dlicari/Italian-Legal-BERT"
+plot_similarity(sent, model_name)
+model_name =  'dbmdz/bert-base-italian-xxl-cased'
+plot_similarity(sent, model_name)
+```
+<img  src="https://huggingface.co/dlicari/Italian-Legal-BERT/resolve/main/semantic_text_similarity.jpg" width="500"/>