Search Results for author:
Found 3 papers, 2 papers with code
Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion
To merge these two forms of knowledge into the dialogue effectively, we design a dynamic virtual knowledge selector and a controller that help to enrich and expand knowledge space.
SceneFormer: Indoor Scene Generation with Transformers
In contrast, we do not use any appearance information, and implicitly learn object relations using the self-attention mechanism of transformers.
Controllable Multi-Character Psychology-Oriented Story Generation
In our work, we aim to design an emotional line for each character that considers multiple emotions common in psychological theories, with the goal of generating stories with richer emotional changes in the characters.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
