Neural Personalized Response Generation as Domain Adaptation

01/09/2017
by   Weinan Zhang, et al.
0

In this paper, we focus on the personalized response generation for conversational systems. Based on the sequence to sequence learning, especially the encoder-decoder framework, we propose a two-phase approach, namely initialization then adaptation, to model the responding style of human and then generate personalized responses. For evaluation, we propose a novel human aided method to evaluate the performance of the personalized response generation models by online real-time conversation and offline human judgement. Moreover, the lexical divergence of the responses generated by the 5 personalized models indicates that the proposed two-phase approach achieves good results on modeling the responding style of human and generating personalized responses for the conversational systems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/30/2018

Automatic Evaluation of Neural Personality-based Chatbots

Stylistic variation is critical to render the utterances generated by co...
research
09/09/2017

Steering Output Style and Topic in Neural Response Generation

We propose simple and flexible training and decoding methods for influen...
research
11/02/2018

Augmenting Neural Response Generation with Context-Aware Topical Attention

Sequence-to-Sequence (Seq2Seq) models have witnessed a notable success i...
research
09/03/2019

Structuring Latent Spaces for Stylized Response Generation

Generating responses in a targeted style is a useful yet challenging tas...
research
07/29/2016

Personalized Emphasis Framing for Persuasive Message Generation

In this paper, we present a study on personalized emphasis framing which...
research
10/30/2021

EmpBot: A T5-based Empathetic Chatbot focusing on Sentiments

In this paper, we introduce EmpBot: an end-to-end empathetic chatbot. Em...
research
05/31/2019

Content Word-based Sentence Decoding and Evaluating for Open-domain Neural Response Generation

Various encoder-decoder models have been applied to response generation ...

Please sign up or login with your details

Forgot password? Click here to reset