Deep Learning: Language identification using Keras & TensorFlow

@tachyeonz : Source: openclipart.org, license: Public Domain

Read More

Connect On:
Twitter :@tachyeonz

Advertisements

One thought on “Deep Learning: Language identification using Keras & TensorFlow

  1. You said that the goal was predict language of a short text of 140 characters, which is typical for an SMS or a tweet. Wikipedia articles are usually long sentences of grammatically correct language, where SMS or Twitter is full of shortenings, misspellings, abbreviations, and may contain a mix of two languages with English being one of them. This is actually a much harder problem to solve for a neural network, when people who know the language usually have no problem identifying the language of a short text even when grammatically it is a complete gibberish. Did you try your network on real short messages?

    Like

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s