Papers with ShapeIntersection

1 papers
Think Visually: Question Answering through Virtual Imagery (P18-1)

Copied to clipboard

Challenge: Existing models of geometric reasoning are based on visual representations of objects and objects, but they are not based in symbols or words.
Approach: They propose a new deep network architecture that specializes in answering questions that admit latent visual representations and learns to generate and reason over such representations.
Outcome: The proposed model can generate and reason over latent visual representations and is validated by two synthetic benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations