Log In Sign Up

Contrastive Learning with Adversarial Perturbations for Conditional Text Generation

by   Seanie Lee, et al.

Recently, sequence-to-sequence (seq2seq) models with the Transformer architecture have achieved remarkable performance on various conditional text generation tasks, such as machine translation. However, most of them are trained with teacher forcing with the ground truth label given at each time step, without being exposed to incorrectly generated tokens during training, which hurts its generalization to unseen inputs, that is known as the “exposure bias" problem. In this work, we propose to mitigate the conditional text generation problem by contrasting positive pairs with negative pairs, such that the model is exposed to various valid or incorrect perturbations of the inputs, for improved generalization. However, training the model with naive contrastive learning framework using random non-target sequences as negative examples is suboptimal, since they are easily distinguishable from the correct output, especially so with models pretrained with large text corpora. Also, generating positive examples requires domain-specific augmentation heuristics which may not generalize over diverse domains. To tackle this problem, we propose a principled method to generate positive and negative samples for contrastive learning of seq2seq models. Specifically, we generate negative examples by adding small perturbations to the input sequence to minimize its conditional likelihood, and positive examples by adding large perturbations while enforcing it to have a high conditional likelihood. Such “hard” positive and negative pairs generated using our method guides the model to better distinguish correct outputs from incorrect ones. We empirically show that our proposed method significantly improves the generalization of the seq2seq on three text generation tasks - machine translation, text summarization, and question generation.


page 1

page 2

page 3

page 4


CoNT: Contrastive Neural Text Generation

Recently, contrastive learning attracts increasing interests in neural t...

Neural Text Generation with Artificial Negative Examples

Neural text generation models conditioning on given input (e.g. machine ...

Improving Text Generation with Student-Forcing Optimal Transport

Neural language models are often trained with maximum likelihood estimat...

MaskGAN: Better Text Generation via Filling in the ______

Neural text generation models are often autoregressive language models o...

Dutch Humor Detection by Generating Negative Examples

Detecting if a text is humorous is a hard task to do computationally, as...

Calibrating Sequence likelihood Improves Conditional Language Generation

Conditional language models are predominantly trained with maximum likel...

Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation

Neural text generation models are typically trained by maximizing log-li...