Multi-modal Dialogue Generation

1 papers with code • 1 benchmarks • 3 datasets

Image credit: OpenViDial

Most implemented papers

OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts

ShannonAI/OpenViDial 27 Sep 2021

In order to better simulate the real human conversation process, models need to generate dialogue utterances based on not only preceding textual contexts but also visual contexts.