Natural Language Processing
Pre processing Data:
- Tokenizing: Seperating of words or sentences.
- Stop Words: Getting rid of useless words
- Stemming: Converting all words into root.
- Lemmatization: Better than stemming.
- Spech Tagging: Making tuples of words with their tags(nouns, adverbs, adjectives)
- Chunking: Grouping of similar grammar together
- Chinking: Grouping of similar grammar together by selecting all and removing certain kind out.
- Named Entity Recognition: Alternative to chunking/chinking.
- Wordnet: To find synonyms/ antonyms/ meanings of words. Also used to find similarities between words.