With the aim of building next generation virtual assistants that can handle multimodal inputs and perform multimodal actions, we introduce two new datasets (both in the virtual shopping domain), the annotation schema, the core technical tasks, and the baseline models. The code for the baselines and the datasets will be opensourced.
Other
131
stars
36
forks
source link
Fixes several bugs and updates baseline performances; #21 #23
Fixes bugs in action evaluation, response generation evaluation, tf_idf calculations, transformer hidden size hyperparameter