CLFeb 20, 2017

Latent Variable Dialogue Models and their Diversity

arXiv:1702.05962v169 citations
Originality Incremental advance
AI Analysis

This addresses the issue of low diversity in dialogue systems for users, but it is incremental as it builds on existing latent variable approaches.

The authors tackled the problem of boring outputs in deterministic dialogue models by introducing a latent variable model that captures response variability, resulting in more diverse and consistently acceptable outputs compared to baseline models.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes