tag:blogger.com,1999:blog-4042957.post114814863738924836..comments2007-02-19T09:34:58.246-06:00Comments on Confessions of a Cyclist: Natural Language Understanding is Hard#$JohnDhttp://www.blogger.com/profile/10315081070263177342noreply@blogger.comBlogger3125tag:blogger.com,1999:blog-4042957.post-1161159867320782042006-10-18T03:24:00.000-05:002006-10-18T03:24:00.000-05:00Why does George Miller assume language is made up ...Why does George Miller assume language is made up of words with independent meanings, which must then be combined to create meaning in a text?RobFhttp://www.chaoticlanguage.comnoreply@blogger.comtag:blogger.com,1999:blog-4042957.post-1148616682237750352006-05-25T23:11:00.000-05:002006-05-25T23:11:00.000-05:00Yes, I'd agree it's a little overstated. But parse...Yes, I'd agree it's a little overstated. But parsers that attempt to convert English to something like predicate calculus choke way before even a few thousand interpretations. So, it it's a trillion or a billion or a million -- it's out of reach without taking just the right approach, including defining context as precisely as possible up front and adjusting it as more is known.#$JohnDhttp://www.blogger.com/profile/10315081070263177342noreply@blogger.comtag:blogger.com,1999:blog-4042957.post-1148607714383658632006-05-25T20:41:00.000-05:002006-05-25T20:41:00.000-05:00> . . . has over 3 trillion possible meanings.Isn'...> . . . has over 3 trillion possible meanings.<BR/><BR/>Isn't that a bit melodramatic? Those numbers include 3 meanings of the word "I" and 5 meanings of the word "And", which seems a bit artificially high.Bryanhttp://buxtrosion.comnoreply@blogger.com