Virtually all Wikipedia articles that need one already have a taxobox, which will be far easier to process than the lead sentence, so I'm not sure where the need for natural language processing comes in. Also, are you aware of the existing automatic taxobox system on en.wikipedia ( https://en.wikipedia.org/wiki/Template:Automatic_taxobox).
2012/4/2 Ashwin Ravichandran ashwin107@gmail.com
Agreed, but we will be diving into further classification, won't we?
Imagine.
Elephant: = (Elephantidae Elephas || Elephantidae Loxodonta || Elephantidae Mammuthus)
But, we didn't specify what type of elephant?
Imagine, we have the Asian Elephant:
Then, we know the fact Asian Elephant: = (Elephantidae Elephas)
Whereas African Elephant: = (Elephantidae Loxodonta)
and the genera Extinct: = (Elephantidae Mammuthus).
With the above script, we might not be 100% correct, but at least we are trying for 100. Taxobox generation will be quite easy after that.
Cheers, Ashwin _______________________________________________ Wikitech-l mailing list Wikitech-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wikitech-l