This section will describe the outputs you must see on executing the commands in the previous section:
- After running the commands for tokenizing the sentences and calculating vocabulary length you must see an output as shown in the following screenshot:
- Words are assigned values starting from 1 up to the total number of words (for example, 5,027 in this case). The Embedding layer needs to allocate a vector representation for each word in this vocabulary from index 1 to the largest index. The index of the word at the end of the vocabulary will be 5,027; that means the array must be 5,027 + 1 in length.
- The output after array ...