Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue Agent

07/08/2019
by   Zelin Dai, et al.
1

Multiple sequence to sequence models were used to establish an end-to-end multi-turns proactive dialogue generation agent, with the aid of data augmentation techniques and variant encoder-decoder structure designs. A rank-based ensemble approach was developed for boosting performance. Results indicate that our single model, in average, makes an obvious improvement in the terms of F1-score and BLEU over the baseline by 18.67 In particular, the ensemble methods further significantly outperform the baseline by 35.85

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/05/2019

Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialogue

The training of task-oriented dialogue systems is often confronted with ...
research
08/15/2019

Towards End-to-End Learning for Efficient Dialogue Agent by Modeling Looking-ahead Ability

Learning an efficient manager of dialogue agent from data with little ma...
research
06/07/2021

CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System

Information-seeking dialogue systems, including knowledge identification...
research
05/16/2018

A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation

Natural language generation lies at the core of generative dialogue syst...
research
10/09/2020

On Task-Level Dialogue Composition of Generative Transformer Model

Task-oriented dialogue systems help users accomplish tasks such as booki...
research
01/27/2018

Exploration on Generating Traditional Chinese Medicine Prescription from Symptoms with an End-to-End method

Traditional Chinese Medicine (TCM) is an influential form of medical tre...
research
05/25/2022

Conditional set generation using Seq2seq models

Conditional set generation learns a mapping from an input sequence of to...

Please sign up or login with your details

Forgot password? Click here to reset