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

[Kilian Evang]

Hi Kais,

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.

the first possibility that comes to my mind is using a chart parser
where producing semantic representations is integrated with the
syntactic parsing process. I.e. directly produce the semantics of each
constituent that you put onto the parse chart. Then you can check each
constituent as to whether its presuppositions are fulfilled in the given
situation. E.g. the constituent "the (yellow block (on the blue block))"
carries the presupposition that there is a yellow block sitting on a
blue block. If that is not the case, you can immediately discard the
constituent.

Cheers,
Kilian

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