I have built a Wikipedia dictionary using the following code:
from gensim.corpora import WikiCorpus, wikicorpus
articles = "enwiki-latest-pages-articles.xml.bz2"
wiki_corpus = WikiCorpus(articles)
wiki_corpus.dictionary.save("wiki_dict.dict")
Now I have a set of text sentences. I want to run a query of these texts against certain words (set of affinity categories), where the definition of these words can be taken out from the wiki corpus.
So for example:
This is the set of text: ["make a lot of money through magic millions website" , "travel through virgin mobile", ...]
This is the set of affinity categories: ["Foodie", "Cooking", ...]
So affinity categories are the words that I want to compare the queries against. However, each of these words must contain a Wikipedia dictionary.