Natural language processing tasks and techniques. Constituency parsing with context-free grammars. Language modeling with n-grams. Bag-of-words model and Naïve Bayes classifier for text categorization. Information retrieval with TF-IDF. Automatic template generation for information extraction. Distributed word representation via Word2Vec (Skip-gram).
- Parser: Parse sentences and extract noun phrases.
python parser.py
- Questions: Answer questions based on a corpus of text.
python questions.py corpus