DeepAI AI Chat
Log In Sign Up

Learning to Predict Persona Information forDialogue Personalization without Explicit Persona Description

by   Wangchunshu Zhou, et al.
Beihang University

Personalizing dialogue agents is important for dialogue systems to generate more specific, consistent, and engaging responses. However, most current dialogue personalization approaches rely on explicit persona descriptions during inference, which severely restricts its application. In this paper, we propose a novel approach that learns to predict persona information based on the dialogue history to personalize the dialogue agent without relying on any explicit persona descriptions during inference. Experimental results on the PersonaChat dataset show that the proposed method can improve the consistency of generated responses when conditioning on the predicted profile of the dialogue agent (i.e. "self persona"), and improve the engagingness of the generated responses when conditioning on the predicted persona of the dialogue partner (i.e. "their persona"). We also find that a trained persona prediction model can be successfully transferred to other datasets and help generate more relevant responses.


page 1

page 2

page 3

page 4


Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training

In this paper, we propose Inverse Adversarial Training (IAT) algorithm f...

Generating Persona-Consistent Dialogue Responses Using Deep Reinforcement Learning

Recent transformer-based open-domain dialogue agents are trained by refe...

"Wait, I'm Still Talking!" Predicting the Dialogue Interaction Behavior Using Imagine-Then-Arbitrate Model

Producing natural and accurate responses like human beings is the ultima...

Personalizing Dialogue Agents: I have a dog, do you have pets too?

Chit-chat models are known to have several problems: they lack specifici...

Dual Task Framework for Improving Persona-grounded Dialogue Dataset

This paper introduces a simple yet effective data-centric approach for t...

Linguistic calibration through metacognition: aligning dialogue agent responses with expected correctness

Open-domain dialogue agents have vastly improved, but still confidently ...

A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation

Unstructured Persona-oriented Dialogue Systems (UPDS) has been demonstra...