Using Soft Constraints To Learn Semantic Models Of Descriptions Of Shapes

Details Using Soft Constraints To Learn Semantic Models Of Descriptions Of Shapes Using Soft Constraints To Learn Semantic Models Of Descriptions Of Shapes

2010-05-28

arxiv.org/abs/1005.5253v1

Computer Science

Computation and Language

8 pages, 8 figures, WCCI'10 Conference

Scientific paper

The contribution of this paper is to provide a semantic model (using soft constraints) of the words used by web-users to describe objects in a language game; a game in which one user describes a selected object of those composing the scene, and another user has to guess which object has been described. The given description needs to be non ambiguous and accurate enough to allow other users to guess the described shape correctly. To build these semantic models the descriptions need to be analyzed to extract the syntax and words' classes used. We have modeled the meaning of these descriptions using soft constraints as a way for grounding the meaning. The descriptions generated by the system took into account the context of the object to avoid ambiguous descriptions, and allowed users to guess the described object correctly 72% of the times.

Affiliated with

Also associated with

No associations

Rating

Using Soft Constraints To Learn Semantic Models Of Descriptions Of Shapes does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Using Soft Constraints To Learn Semantic Models Of Descriptions Of Shapes, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Using Soft Constraints To Learn Semantic Models Of Descriptions Of Shapes will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-15843