Latent Variable Dialogue Models and their Diversity

02/20/2017
by   Kris Cao, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/22/2021

DLVGen: A Dual Latent Variable Approach to Personalized Dialogue Generation

The generation of personalized dialogue is vital to natural and human-li...
research
05/29/2017

Latent Intention Dialogue Models

Developing a dialogue agent that is capable of making autonomous decisio...
research
08/12/2021

Generating Diverse Descriptions from Semantic Graphs

Text generation from semantic graphs is traditionally performed with det...
research
05/19/2016

A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

Sequential data often possesses a hierarchical structure with complex de...
research
09/29/2022

An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation

Open-domain dialogue systems aim to interact with humans through natural...
research
04/21/2022

A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation

Towards building intelligent dialogue agents, there has been a growing i...
research
01/27/2017

Adversarial Evaluation of Dialogue Models

The recent application of RNN encoder-decoder models has resulted in sub...

Please sign up or login with your details

Forgot password? Click here to reset