A novel repetition normalized adversarial reward for headline generation

02/19/2019
by   Peng Xu, et al.
0

While reinforcement learning can effectively improve language generation models, it often suffers from generating incoherent and repetitive phrases paulus2017deep. In this paper, we propose a novel repetition normalized adversarial reward to mitigate these problems. Our repetition penalized reward can greatly reduce the repetition rate and adversarial training mitigates generating incoherent phrases. Our model significantly outperforms the baseline model on ROUGE-1 (+3.24), ROUGE-L (+2.25), and a decreased repetition-rate (-4.98%).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/09/2019

Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning

Sensational headlines are headlines that capture people's attention and ...
research
03/24/2020

Learning Compact Reward for Image Captioning

Adversarial learning has shown its advances in generating natural and di...
research
10/11/2018

Generating Diverse Numbers of Diverse Keyphrases

Existing keyphrase generation studies suffer from the problems of genera...
research
04/29/2020

Counterfactual Off-Policy Training for Neural Response Generation

Learning a neural response generation model on data synthesized under th...
research
08/22/2018

Keyphrase Generation with Correlation Constraints

In this paper, we study automatic keyphrase generation. Although convent...
research
11/02/2021

Integrating Pretrained Language Model for Dialogue Policy Learning

Reinforcement Learning (RL) has been witnessed its potential for trainin...
research
06/01/2022

RLSS: A Deep Reinforcement Learning Algorithm for Sequential Scene Generation

We present RLSS: a reinforcement learning algorithm for sequential scene...

Please sign up or login with your details

Forgot password? Click here to reset