Update README.md

README.md

@@ -95,23 +95,64 @@ model_name = "real-jiakai/bert-base-chinese-finetuned-squadv2"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForQuestionAnswering.from_pretrained(model_name)
 
-# Prepare the inputs
-question = "your_question"
-context = "your_context"
-inputs = tokenizer(
-    question,
-    context,
-    add_special_tokens=True,
-    return_tensors="pt"
-)
-
-# Get the answer
-start_scores, end_scores = model(**inputs)
-start_index = torch.argmax(start_scores)
-end_index = torch.argmax(end_scores)
-answer = tokenizer.convert_tokens_to_string(
-    tokenizer.convert_ids_to_tokens(inputs["input_ids"][0][start_index:end_index+1])
-)
+def get_answer(question, context, threshold=0.0):
+    # Tokenize input with maximum sequence length of 384
+    inputs = tokenizer(
+        question,
+        context,
+        return_tensors="pt",
+        max_length=384,
+        truncation=True
+    )
+    
+    with torch.no_grad():
+        outputs = model(**inputs)
+        start_logits = outputs.start_logits[0]
+        end_logits = outputs.end_logits[0]
+        
+        # Calculate null score (score for predicting no answer)
+        null_score = start_logits[0].item() + end_logits[0].item()
+        
+        # Find the best non-null answer, excluding [CLS] position
+        # Set logits at [CLS] position to negative infinity
+        start_logits[0] = float('-inf')
+        end_logits[0] = float('-inf')
+        
+        start_idx = torch.argmax(start_logits)
+        end_idx = torch.argmax(end_logits)
+        
+        # Ensure end_idx is not less than start_idx
+        if end_idx < start_idx:
+            end_idx = start_idx
+            
+        answer_score = start_logits[start_idx].item() + end_logits[end_idx].item()
+        
+        # If null score is higher (beyond threshold), return "no answer"
+        if null_score - answer_score > threshold:
+            return "Question cannot be answered based on the given context."
+            
+        # Otherwise, return the extracted answer
+        tokens = tokenizer.convert_ids_to_tokens(inputs["input_ids"][0])
+        answer = tokenizer.convert_tokens_to_string(tokens[start_idx:end_idx+1])
+        
+        # Check if answer is empty or contains only special tokens
+        if not answer.strip() or answer.strip() in ['[CLS]', '[SEP]']:
+            return "Question cannot be answered based on the given context."
+            
+        return answer.strip()
+
+questions = [
+    "本届第十五届珠海航展的亮点和主要展示内容是什么？",
+    "珠海杀人案发生地点？"
+]
+
+context = '第十五届中国国际航空航天博览会（珠海航展）于2024年11月12日至17日在珠海国际航展中心举行。本届航展吸引了来自47个国家和地区的超过890家企业参展，展示了涵盖"陆、海、空、天、电、网"全领域的高精尖展品。其中，备受瞩目的中国空军"八一"飞行表演队和"红鹰"飞行表演队，以及俄罗斯"勇士"飞行表演队同台献技，为观众呈现了精彩的飞行表演。此外，本届航展还首次开辟了无人机、无人船演示区，展示了多款前沿科技产品。'
+
+for question in questions:
+    answer = get_answer(question, context)
+    print(f"问题: {question}")
+    print(f"答案: {answer}")
+    print("-" * 50)
 ```
 
 ## Limitations and Bias