[For_Iconoclasm]

I worked on a natural language processing project as my required directed study in college. We focused on language generation and took an extremely naïve approach to the problem since it turns out that literature on alternative types of language generation (as opposed to simple generation from n-grams) is not well-proliferated.

Needless to say, it was very hard. Semantic representation by itself is very difficult to tackle; AI in general far off from simulating the wit and ingenuity of a human being's writing, though I don't believe it will be like that forever.

For the curious: we didn't get very far into the project, but our next move was going to be trying to combine WordNet, FrameNet, and VerbNet to create stories that sounded like they described something plausible. We only got a bit past "Colorless green ideas sleep furiously," though.

It's something that I say I want to hack on again someday, but I don't know if I will. The two of us have other code projects right now.

[uniclaude]

Not that your comment is wrong in any manner but I must admit that I cannot understand its relationship with the article.