Latent Variable Dialogue Models and their Diversity
2017-02-20EACL 2017Code Available0· sign in to hype
Kris Cao, Stephen Clark
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/timbmg/DIAL-LVpytorch★ 0
Abstract
We present a dialogue generation model that directly captures the variability in possible responses to a given input, which reduces the `boring output' issue of deterministic dialogue models. Experiments show that our model generates more diverse outputs than baseline models, and also generates more consistently acceptable output than sampling from a deterministic encoder-decoder model.