Interpretation score of bilstm-crf in NER_ sentence

If you have any doubts about the following , You may need to read what I wrote in my previous article BiLSTM-CRF Explanation
CRF+BiLSTM The code is interpreted step by step

Explain

This function is used to calculate the score of the best path , This is the same as the previous one Forward_algorithm Is different , The main difference is that score_sentence It is used to record the score of the previous best path at the current time , and Forward_algorithm It records the scores of all paths before reaching the current time .

give an example

The process

The result of the calculation is ️
$$\begin{gathered} scor{e}_1=0+t_{3\to 0}+e_0+t_{0\to 1}+e_1+t_{1\to 0}+e_0+t_{0\to 2}+e_2 \\ scor{e}_2=scor{e}_1+t_{2\to 4} \end{gathered}$$

Code

 def score_sentence(self,e_score, tags):
    # e_score (BATCH_SIZE,SEQ_LEN,tags_size) tags (BATCH_SIZE,SEQ_LEN)
    # score (BATCH_SIZE,1)
    score = torch.zeros((BATCH_SIZE,1),device=device)

    #  Add a start tag to each tag sequence <START> tags (BATCH_SIZE,SEQ_LEN+1)
    tags = torch.cat([torch.tensor([self.s2i[START_TAG] for _ in range(BATCH_SIZE)], dtype=torch.long).reshape(BATCH_SIZE,1), tags],dim=-1)
    for size in range(BATCH_SIZE):
      for i, feat in enumerate(e_score[size]):
        score[size] +=  self.t_score[tags[size,i + 1], tags[size,i]] + feat[tags[size,i + 1]]
    	score[size] += self.t_score[self.s2i[STOP_TAG], tags[size,-1]]
    return score