Exploiting Persona Information for Diverse Generation of Conversational Responses

05/29/2019
by   Haoyu Song, et al.
0

In human conversations, due to their personalities in mind, people can easily carry out and maintain the conversations. Giving conversational context with persona information to a chatbot, how to exploit the information to generate diverse and sustainable conversations is still a non-trivial task. Previous work on persona-based conversational models successfully make use of predefined persona information and have shown great promise in delivering more realistic responses. And they all learn with the assumption that given a source input, there is only one target response. However, in human conversations, there are massive appropriate responses to a given input message. In this paper, we propose a memory-augmented architecture to exploit persona information from context and incorporate a conditional variational autoencoder model together to generate diverse and sustainable conversations. We evaluate the proposed model on a benchmark persona-chat dataset. Both automatic and human evaluations show that our model can deliver more diverse and more engaging persona-based responses than baseline approaches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/03/2021

DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation

Having engaging and informative conversations with users is the utmost g...
research
05/13/2020

Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation

Neural conversation models are known to generate appropriate but non-inf...
research
11/06/2019

Guiding Variational Response Generator to Exploit Persona

Leveraging persona information of users in Neural Response Generators (N...
research
05/22/2022

AFEC: A Knowledge Graph Capturing Social Intelligence in Casual Conversations

This paper introduces AFEC, an automatically curated knowledge graph bas...
research
04/16/2021

Human-like informative conversations: Better acknowledgements using conditional mutual information

This work aims to build a dialogue agent that can weave new factual cont...
research
11/19/2018

A Trustworthy, Responsible and Interpretable System to Handle Chit-Chat in Conversational Bots

Most often, chat-bots are built to solve the purpose of a search engine ...
research
04/27/2023

CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants

A wave of new task-based virtual assistants has been fueled by increasin...

Please sign up or login with your details

Forgot password? Click here to reset