分词语言模型make_ngram疑问

[LRY1994]

如果语言模型是分词的，is_character_based_==False, 分词语言模型只有遇到space_id才打分
make_ngram[4]得到截止当前帧固定长度窗口内的词语。
如果输出token没有SPACE_ID_，只取当前帧固定长度窗口内的词语，前面的词不就没有取到的机会吗？

// language model scoring
          float ngram_score = 0.0;
          if (ext_scorer != nullptr ) {
              if (hotwords_scorer != nullptr && 
                !hotwords_scorer->hotwords_dict.empty() &&
                !(hotwords_scorer->is_character_based ^ ext_scorer->is_character_based()) &&
                hotwords_scorer->window_length >= ext_scorer->get_max_order()) {
                  std::vector<std::string>::const_iterator first = ngram.end() - ext_scorer->get_max_order();
                  std::vector<std::string>::const_iterator last  = ngram.end();
                  std::vector<std::string> slice_ngram(first, last);
                  ngram_score = ext_scorer->get_log_cond_prob(slice_ngram) * ext_scorer->alpha + ext_scorer->beta;
              } else {
                  if (c == space_id || ext_scorer->is_character_based()) {
                      // skip scoring the space
                      if (ext_scorer->is_character_based()) {
                          prefix_to_score = prefix_new;
                      } else {
                          prefix_to_score = prefix;
                      }
                      ngram = ext_scorer->make_ngram(prefix_to_score);// 通过调用make_ngram[3]函数获取当前前缀中的Ngram
                      ngram_score = ext_scorer->get_log_cond_prob(ngram) * ext_scorer->alpha + ext_scorer->beta; //调用语言模型计算上面公式中的条件概率。
                  }
              }
          }

std::vector<std::string> Scorer::make_ngram(PathTrie* prefix) {
  std::vector<std::string> ngram;
  PathTrie* current_node = prefix;
  PathTrie* new_node = nullptr;

  for (int order = 0; order < max_order_; order++) {
    std::vector<int> prefix_vec;

    if (is_character_based_) {
      new_node = current_node->get_path_vec(prefix_vec, SPACE_ID_, 1);
      current_node = new_node;
    } else {
      new_node = current_node->get_path_vec(prefix_vec, SPACE_ID_);
      current_node = new_node->parent;  // Skipping spaces
    }

    // reconstruct word
    std::string word = vec2str(prefix_vec);
    ngram.push_back(word);

    if (new_node->character == -1) {
      // No more spaces, but still need order
      for (int i = 0; i < max_order_ - order - 1; i++) {
        ngram.push_back(START_TOKEN);
      }
      break;
    }
  }
  std::reverse(ngram.begin(), ngram.end());
  return ngram;
}