bigram solution

run2.py

@@ -0,0 +1,36 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForMaskedLM
+import sys
+
+tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
+model = AutoModelForMaskedLM.from_pretrained("bert-base-uncased")
+
+for line in sys.stdin:
+    splitted_line = line.split("\t")
+    left_context = splitted_line[6].split(" ")[-1]
+    right_context = splitted_line[7].split(" ")[0]
+
+    word = "[MASK]"
+
+    text = f"{left_context} {word} {right_context}"
+
+    input_ids = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt", max_length=512, truncation=True)
+
+    mask_token_index = torch.where(input_ids == tokenizer.mask_token_id)[1][0]
+
+    with torch.inference_mode():
+        outputs = model(input_ids)
+        predictions = outputs[0][0, mask_token_index].softmax(dim=0)
+
+    top_k = 500
+    top_k_tokens = torch.topk(predictions, top_k).indices.tolist()
+    result = ''
+    prob_sum = 0
+    for token in top_k_tokens:
+        word = tokenizer.convert_ids_to_tokens([token])[0]
+        prob = predictions[token].item()
+        prob_sum += prob 
+        result += f"{word}:{prob} "
+    diff = 1.0 - prob_sum
+    result += f":{diff}"
+    print(result)