Process Synonyms¶

This notebook uses a combination of Python data science libraries and the Google Natural Language API (machine learning) to expand the vocabulary of the chatbot by generating synonyms for topics created in the previous notebook.

In [ ]:

!pip install inflect

Hit Reset Session > Restart, then resume with the following cells.

In [ ]:

# Only need to do this once...
import nltk
nltk.download('stopwords')
nltk.download('wordnet')

In [ ]:

from nltk.corpus import stopwords
stop = set(stopwords.words('english'))

In [ ]:

from google.cloud import datastore

In [ ]:

datastore_client = datastore.Client()

In [ ]:

client = datastore.Client()
query = client.query(kind='Topic')
results = list(query.fetch())

In [ ]:

import inflect
plurals = inflect.engine()

Extract Synonyms with Python¶

Split the topic into words and use PyDictionary to look up synonyms in a "thesaurus" for each word. Store these in Datastore and link them back to the topic. Note this section uses the concept of "stop words" to filter out articles and other parts of speech that don't contribute to meaning of the topic.

In [ ]:

from nltk.corpus import wordnet
from sets import Set

for result in results:
  for word in result.key.name.split():
    
    if word in stop:
        continue

    
    synonyms = Set()
    for syn in wordnet.synsets(word):
      
      if ".n." in str(syn):

        for l in syn.lemmas():
          lemma = l.name()
          if (lemma.isalpha()):
            synonyms.add(lemma)
            synonyms.add(plurals.plural(lemma))
      
      if ".a." in str(syn):
        synonyms = Set()
        break

    print result.key.name, word, synonyms
    
    kind = 'Synonym'
    synonym_key = datastore_client.key(kind, result.key.name)

    synonym = datastore.Entity(key=synonym_key)
    synonym['synonym'] = result.key.name

    datastore_client.put(synonym)
    
    synonym_key = datastore_client.key(kind, word)

    synonym = datastore.Entity(key=synonym_key)
    synonym['synonym'] = result.key.name

    datastore_client.put(synonym)
    
    for dictionary_synonym in synonyms:
      
      synonym_key = datastore_client.key(kind, dictionary_synonym)

      synonym = datastore.Entity(key=synonym_key)
      synonym['synonym'] = result.key.name

      datastore_client.put(synonym)
      
    synonym_key = datastore_client.key(kind, plurals.plural(word))

    synonym = datastore.Entity(key=synonym_key)
    synonym['synonym'] = result.key.name

    datastore_client.put(synonym)
    

In [ ]: