Hi I was recently building a sentiment analysis chatbot with the platform NLTK (Natural Language Toolkit). But i was having difficulties in the Feed Forward Neural net with 2 hidden layers. It returns error and im having difficulty with the deep learning and ML algorithms. I have specified the code below.
# nltk_utils.py
import numpy as np
import nltk
# nltk.download('punkt')
from nltk.stem.porter import PorterStemmer
stemmer = PorterStemmer()
def tokenize(sentence):
"""
split sentence into array of words/tokens
a token can be a word or punctuation character, or number
"""
return nltk.word_tokenize(sentence)
def stem(word):
"""
stemming = find the root form of the word
examples:
words = ["organize", "organizes", "organizing"]
words = [stem(w) for w in words]
-> ["organ", "organ", "organ"]
"""
return stemmer.stem(word.lower())
def bag_of_words(tokenized_sentence, words):
"""
return bag of words array:
1 for each known word that exists in the sentence, 0 otherwise
example:
sentence = ["hello", "how", "are", "you"]
words = ["hi", "hello", "I", "you", "bye", "thank", "cool"]
bog = [ 0 , 1 , 0 , 1 , 0 , 0 , 0]
"""
# stem each word
sentence_words = [stem(word) for word in tokenized_sentence]
# initialize bag with 0 for each word
bag = np.zeros(len(words), dtype=np.float32)
for idx, w in enumerate(words):
if w in sentence_words:
bag[idx] = 1
return bag
I tried to modify intents.json
with possible patterns and responses and re-run the training but it did not work. I am currently working for a chatbot development services company and they have knowledge in SciPay and SpaCY. Would that be helpful here?