Low-Resource Response Generation with Template Prior

09/26/2019
by   Wei Wu, et al.
0

We study open domain response generation with limited message-response pairs. The problem exists in real-world applications but is less explored by the existing work. Since the paired data now is no longer enough to train a neural generation model, we consider leveraging the large scale of unpaired data that are much easier to obtain, and propose response generation with both paired and unpaired data. The generation model is defined by an encoder-decoder architecture with templates as prior, where the templates are estimated from the unpaired data as a neural hidden semi-markov model. By this means, response generation learned from the small paired data can be aided by the semantic and syntactic knowledge in the large unpaired data. To balance the effect of the prior and the input message to response generation, we propose learning the whole generation model with an adversarial approach. Empirical studies on question response generation and sentiment response generation indicate that when only a few pairs are available, our model can significantly outperform several state-of-the-art response generation models in terms of both automatic and human evaluation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/30/2018

Learning Neural Templates for Text Generation

While neural, encoder-decoder models have had significant empirical succ...
research
06/14/2019

Neural Response Generation with Meta-Words

We present open domain response generation with meta-words. A meta-word ...
research
04/04/2020

Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks

We study multi-turn response generation for open-domain dialogues. The e...
research
02/04/2020

Variational Template Machine for Data-to-Text Generation

How to generate descriptions from structured data organized in tables? E...
research
02/24/2020

Low-Resource Knowledge-Grounded Dialogue Generation

Responding with knowledge has been recognized as an important capability...
research
09/12/2018

Retrieval-Enhanced Adversarial Training for Neural Response Generation

Dialogue systems are usually built on either generation-based or retriev...
research
04/30/2016

Response Selection with Topic Clues for Retrieval-based Chatbots

We consider incorporating topic information into message-response matchi...

Please sign up or login with your details

Forgot password? Click here to reset