DeepAI AI Chat
Log In Sign Up

Rethinking Exposure Bias In Language Modeling

by   Yifan Xu, et al.

Exposure bias describes the phenomenon that a language model trained under the teacher forcing schema may perform poorly at the inference stage when its predictions are conditioned on its previous predictions unseen from the training corpus. Recently, several generative adversarial networks (GANs) and reinforcement learning (RL) methods have been introduced to alleviate this problem. Nonetheless, a common issue in RL and GANs training is the sparsity of reward signals. In this paper, we adopt two simple strategies, multi-range reinforcing, and multi-entropy sampling, to amplify and denoise the reward signal. Our model produces an improvement over competing models with regards to BLEU scores and road exam, a new metric we designed to measure the robustness against exposure bias in language models.


Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models

In unsupervised data generation tasks, besides the generation of a sampl...

Quantifying Exposure Bias for Neural Language Generation

The exposure bias problem refers to the training-inference discrepancy c...

Teacher Forcing Recovers Reward Functions for Text Generation

Reinforcement learning (RL) has been widely used in text generation to a...

Collaborative Training of GANs in Continuous and Discrete Spaces for Text Generation

Applying generative adversarial networks (GANs) to text-related tasks is...

A Representation Modeling Based Language GAN with Completely Random Initialization

Text generative models trained via Maximum Likelihood Estimation (MLE) s...

Elucidating the Exposure Bias in Diffusion Models

Diffusion models have demonstrated impressive generative capabilities, b...

Generalization and Memorization: The Bias Potential Model

Models for learning probability distributions such as generative models ...