如何理解張量流中的'viterbi_decode'

Question

HMM中使用的傳統維特比算法具有起始概率矩陣（ 維特比算法wiki ），但是張量流中的維特比 解碼參數僅需要轉移概率矩陣和發射概率矩陣 。 怎么理解呢？

def viterbi_decode(score, transition_params):
  """Decode the highest scoring sequence of tags outside of 
  TensorFlow.

  This should only be used at test time.

  Args:
    score: A [seq_len, num_tags] matrix of unary potentials.
    transition_params: A [num_tags, num_tags] matrix of binary potentials.

  Returns:
    viterbi: A [seq_len] list of integers containing the highest scoring tag
    indicies.
    viterbi_score: A float containing the score for the Viterbi 
    sequence.
  """

Answer 1

Tensorflow中的維特比算法不需要初始概率矩陣，因為它通過為所有狀態賦予零概率來開始解碼。

這意味着它從狀態0開始。

您可以在此處檢查實現。

Answer 2

我已經創建了完整的詳細教程，並帶有帶有tensorflow的viterbi算法的示例，您可以在這里查看：

假設您的數據如下所示：

# logits :       A [batch_size, max_seq_len, num_tags] tensor of unary potentials to use as input to the CRF layer.

# labels_a :     A [batch_size, max_seq_len] matrix of tag indices for which we compute the log-likelihood.

# sequence_len : A [batch_size] vector of true sequence lengths.

然后

log_likelihood , transition_params = tf.contrib.crf.crf_log_likelihood(logits,labels_a,sequence_len)

#return of crf log_likelihood function

# log_likelihood: A scalar containing the log-likelihood of the given sequence of tag indices.

# transition_params: A [num_tags, num_tags] transition matrix. 

# This is either provided by the caller or created in this function.

現在我們可以計算維特比分數：

# score: A [seq_len, num_tags] matrix of unary potentials.
# transition_params: A [num_tags, num_tags] matrix of binary potentials.

筆記本鏈接