Publication

Relational Graph Representation Learning for Open-Domain Question Answering

AbstractWe introduce a relational graph neural network with bi-directional attention mechanism and hierarchical representation learning for open-domain question answering task. Our model can learn contextual representation by jointly learning and updating the query, knowledge graph, and document representations. The experiments suggest that our model achieves state-of-the-art on the WebQuestionsSP benchmark.

Download publication

Related Resources

See what’s new.

Project

01/03/2023

Using AI to Optimize Construction Design

How can we leverage AI to make construction design processes more…

Publication

01/01/2001

A Service Brokerage Deployment Architecture

As more and different services appear over the Internet, there is a…

Publication

01/01/2008

Video Browsing by Direct Manipulation

We present a method for browsing videos by directly dragging their…

Publication

01/01/2015

Folding Angle Regulation by Curved Crease Design for Self-Assembling Origami Propellers

This paper describes a method for manufacturing complex three…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us