Created
April 13, 2017 17:35
-
-
Save anujdutt9/440739592e0251ad06b6c37be25f5351 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Step1: Training Data and Preprocessing | |
# a) Tokenize the Input text (sentence to words) | |
# b) Form the Vocabulary and remove Infrequent words | |
# c) Add "Start" and "End" Tokens to the sentences | |
# Vocabulary Size: 8000 words | |
vocab_size = 8000 | |
# Token to replace the infrequent words | |
unknown_token = 'Unknown_Token' | |
# Sentence start and end tokens | |
sentence_start_token = 'Sentence_Start' | |
sentence_end_token = 'Sentence_End' | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment