Update app.py

app.py

@@ -83,9 +83,6 @@ def process_entity(batch, model, device):
     # Extract the [CLS] token embedding (first token)
     spaBERT_embedding = spaBERT_embedding[:, 0, :].detach()  # [batch_size, hidden_size]
 
-    #pivot_token_len = batch['pivot_token_len'].item()
-    #pivot_embeddings = embeddings[:, :pivot_token_len, :]
-
     #return pivot_embeddings.cpu().numpy(), input_ids.cpu().numpy()
     return spaBERT_embedding, input_ids
 
@@ -114,10 +111,12 @@ def get_bert_embedding(review_text):
     bert_embedding = outputs.last_hidden_state[:, 0, :].detach()     #CLS Token
     return bert_embedding
 
+#Get SpaBERT Embedding for geo-entity
 def get_spaBert_embedding(entity):
     entity_index = entity_index_dict.get(entity.lower(), None)
     return spaBERT_embeddings[entity_index]
 
+#Go through each review, identify all geo-entities, then extract their SpaBERT embedings
 def processSpatialEntities(review, nlp):
     doc = nlp(review)
     entity_spans = [(ent.start, ent.end, ent.text, ent.label_) for ent in doc.ents]