Update README.md

README.md

@@ -22,7 +22,7 @@ model_name = "NchuNLP/Chinese-Question-Answering"
 tokenizer = BertTokenizerFast.from_pretrained(model_name)
 model = BertForQuestionAnswering.from_pretrained(model_name)
 
-# a) Get predictions
+# a) Get predictions 
 nlp = pipeline('question-answering', model=model, tokenizer=tokenizer)
 QA_input = {
     'question': '中興大學在哪裡？',
@@ -30,6 +30,46 @@ QA_input = {
 }
 res = nlp(QA_input)
 
+# b) Inside the Question answering pipeline
+
+inputs = tokenizer(query, text, return_tensors="pt",padding=True, truncation=True, max_length=512, stride=256)
+outputs = model(**inputs)
+
+sequence_ids = inputs.sequence_ids()
+# Mask everything apart from the tokens of the context
+mask = [i != 1 for i in sequence_ids]
+# Unmask the [CLS] token
+mask[0] = False
+mask = torch.tensor(mask)[None]
+
+start_logits[mask] = -10000
+end_logits[mask] = -10000
+
+start_probabilities = torch.nn.functional.softmax(start_logits, dim=-1)[0]
+end_probabilities = torch.nn.functional.softmax(end_logits, dim=-1)[0]
+
+scores = start_probabilities[:, None] * end_probabilities[None, :]
+
+max_index = scores.argmax().item()
+start_index = max_index // scores.shape[1]
+end_index = max_index % scores.shape[1]
+
+
+inputs_with_offsets = tokenizer(query, text, return_offsets_mapping=True)
+offsets = inputs_with_offsets["offset_mapping"]
+
+start_char, _ = offsets[start_index]
+_, end_char = offsets[end_index]
+answer = text[start_char:end_char]
+
+result = {
+    "answer": answer,
+    "start": start_char,
+    "end": end_char,
+    "score": scores[start_index, end_index],
+}
+print(result)
+
 ```
 
 ## Authors