DeepAI AI Chat
Log In Sign Up

Retrieval-Enhanced Adversarial Training for Neural Response Generation

by   Qingfu Zhu, et al.
Harbin Institute of Technology

Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models. In this paper, we propose a Retrieval-Enhanced Adversarial Training (REAT) method for neural response generation. Distinct from existing ap- proaches, the REAT method leverages an encoder-decoder framework in terms of an adversarial training paradigm, while taking advantage of N-best response candidates from a retrieval-based system to construct the discriminator. An empirical study on a large scale public available benchmark dataset shows that the REAT method significantly outper- forms the vanilla Seq2Seq model as well as the conventional adversarial training approach.


page 1

page 2

page 3

page 4


Counterfactual Off-Policy Training for Neural Response Generation

Learning a neural response generation model on data synthesized under th...

Neural Open Information Extraction

Conventional Open Information Extraction (Open IE) systems are usually b...

HeroNet: A Hybrid Retrieval-Generation Network for Conversational Bots

Using natural language, Conversational Bot offers unprecedented ways to ...

Boosting Naturalness of Language in Task-oriented Dialogues via Adversarial Training

The natural language generation (NLG) module in a task-oriented dialogue...

An Adversarially-Learned Turing Test for Dialog Generation Models

The design of better automated dialogue evaluation metrics offers the po...

A Study on FGSM Adversarial Training for Neural Retrieval

Neural retrieval models have acquired significant effectiveness gains ov...

Low-Resource Response Generation with Template Prior

We study open domain response generation with limited message-response p...