News for hackers. Stuff that matters.
Re:Avoiding NLP At All Costs by omarish on Monday November 17, 2008 @09:32AM (#366883)
http://nltk.sourceforge.net/

it's not that hard; you just have to know when to use it.

Re:Avoiding NLP At All Costs by ntoshev on Monday November 17, 2008 @09:50AM (#366905)
NLTK uses statistical approach, which it seems he doesn't consider to be "NLP". TF-IDF is also part of that statistical approach. He seems to be talking about the old school rule-based natural language understanding.
Re:Avoiding NLP At All Costs by nihilocrat on Monday November 17, 2008 @10:25AM (#366941)
If rule-based NLP is what he's truly referring to, he is actually very much on the money. Rule-based NLP gets too complicated too quickly and is useless when analyzing a language other than the target language or analyzing a piece of text that is poorly-formed (bad grammar/spelling) or heavily peppered with loan words and loan constructions.

Much like how Good Old-Fashioned AI has proven to be cumbersome and non-analogous to how biological brains actually work, rule-based NLP is flawed at its core. Statistical NLP has proven to be much more powerful, extensible, and tolerant to near-misses.