Announcing Text Processing APIs

If you liked the NLTK demos, then you’ll love the text processing APIs. They provide all the functionality of the demos, plus a little bit more, and return results in JSON. Requests can contain up to 10,000 characters, instead of the 1,000 character limit on the demos, and you can do up to 100 calls per day. These limits may change in the future depending on usage & demand. If you’d like to do more, please fill out this survey to let me know what your needs are.

  • Pingback: Tweets that mention Announcing Text Processing APIs «streamhacker.com -- Topsy.com()

  • lahwran

    I could use some full python examples, instead of your incomplete examples in the posts – could you perhaps include the code used to generate the accuracy numbers as well, so people can easily verify what you’ve found and then also maybe the call that actually does whatever it is that the post is showing? in the case I’m examining at the moment, I’m trying to use your braubt pos tagger set, and I’m having a hard time piecing together everything you did from the docs and what you said.

  • http://streamhacker.com/ Jacob Perkins

    Accuracy is calculated using TaggerI.evaluate() (inherited by every tagger) with the test sentences as the gold standard. The key thing for creating the braubt tagger is using the backoff_tagger function defined in part 1. Once you train the raubt tagger using backoff_tagger, you just pass that in to the FastBrillTaggerTrainer with the templates. But you’re right that all the pieces are disconnected, and I plan on writing some more articles on POS tagging, so I’ll be sure to include complete examples when I do so.

  • guest

    what’s the difference between this and just running NLTK on your own computer?

    Also, by “free and open” does that mean all the software and data is under a Free Software license?

  • http://streamhacker.com/ Jacob Perkins

    The API is aimed at people that don’t want to run NLTK themselves. “free and open” in this case means free as in beer and no accounts/authentication required, and has nothing to do with licensing.

  • http://www.ashwinjayaprakash.com/ Ashwin Jayaprakash

    Sentiment analysis demo is fun. It’s fast too.