[Corpora-List] Semantic parsing for the robot commands corpus by integrating spatial knowledge

[Mike Maxwell]

> On 07/09/13 08:55, Kais Dukes wrote:
>> Surely there must be a good way to use spatial knowledge while
>> parsing? Could my idea of modifying the non-directional dependency
>> parser work? The parser could then leverage a relational knowledge
>> base for each scene, e.g. if the parser knew that the red block is on
>> the yellow block, it could produce the correct parse tree for the
>> above example.

I believe that shrdlu used that sort of knowledge to narrow its 
interpretations.  The problem was that the technique didn't generalize 
to more complex situations than "blocks world."
-- 
    Mike Maxwell
    "The biggest danger is not ignorance,
    but the illusion of knowledge."
    --Stephen Hawking

_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora