On Wed, Sep 26, 2012 at 4:13 PM, ARAKAWA Naoya <[email protected]> wrote: > anaphor resolution ... > I once tried to pursue the issue of co-reference following the line of > SDRT (Segmented Discourse Representation Theory), but found > the issue very hard, as it requires a lot of world knowledge
As I have argued elsewhere, "discourse" involves redefining words and worlds continuously. In the general case everything means something different to everybody depending their audience, and their worlds are differently constructed, you may have a catholic mom while I am an aborigine orphan etc. And if you select 20 random people and rigorously investigate what they think of some iconic text, like a Jesus parable, they will conclude 40 different things. The magic of discourse is a) that there is method to the madness of producing N interpretations, where N close to infinity and b) that in a select few cases, not unlike the collapse of the wave function, this infinity collapses to the desired outcome. Most likely visual scenes are evoked/involved in which we easily select the desired outcomes out of other nonsensical interpretations. As the desired outcomes include a lot of internal/invisible states of objects and animals loads of great models of such internals are needed. AT ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968 Powered by Listbox: http://www.listbox.com
