Using NLP to Optimize Learning a Foreign Language.

Learning Mandarin in a More Fun and Efficient Way

Learning a language can be very boring. I’ve traveled my entire life, and despite having spent the majority of my life in different countries I’ve always considered myself to not be the best at learning languages. My entire outlook on learning languages changed when somebody I was with went on a rant about how boring Chinese was to learn.

The thought of a language being boring was odd to me, but I saw where he was coming from. This conversation took place after my first Chinese lesson that I signed up for while living in Taipei, Taiwan. And, flipping through the book there were very few topics that were interesting. Sure, they might be necessary. But, it is boring to talk about the location of the bathroom in any language!

The epiphany hit me in the form of a question. Am I really bad at languages? Or, do I just get bored easily and lack the will power to plow through the “necessary” material before getting to something I can sink my teeth into? In an effort to actually learn Mandarin, I have created a little project that uses wikipedia articles in Chinese to create vocabulary lists of topics that I find interesting and am more likely to use.

There are a lot of words out there, but it only takes a few keywords and context to decipher the meaning of surrounding words. This project uses IF-IDF to develop a vocabulary list of topical words. Everything is focused on…