All NLP is about mapping the internal statistical dependencies of language, missing the point that language is a *communication protocol*.
-
Yes I think this is pretty widely accepted in NLP, see e.g. work from Roth, Mooney, Zettlemoyer, Barzilay, etc +
I can't remember a single NLP paper that included the concept of agent or environment.
-
-
well, actually I can remember one, but it was extremely fringe (getting agents to invent their own language)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
here's a random example, would this count? http://dl.acm.org/citation.cfm?id=1687892 …
-
anyway, getting informational content requires syntactic parsing, which in turn leans heavily on statistical regularities+
- Show replies
New conversation -
-
-
check out work by
@yoavartzi for example: https://scholar.google.com/citations?user=XuQW7ogAAAAJ … (there are many others) -
also, of course communication is implicit in many works, esp in e.g. summarization: http://research.microsoft.com/en-us/um/people/cyl/download/papers/lexical-chains.pdf …
End of conversation
New conversation -
-
-
if you mean the inclusion of context, of information on the agent via extra-linguistics features there is
-
if you mean the inclusion of the environment in devising action from text analysis there is too..
End of conversation
New conversation -
-
-
it's more than agent/environment, theoretically this paper covers many aspects: http://projects.ict.usc.edu/nld/semdial2011/proceedings/semdial2011_larsson.pdf …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.