Қарсыласу арқылы толықтыру
Related Papers
AdvAug: Robust Adversarial Augmentation for Neural Machine Translation
AbstractIn this paper, we propose a new adversarial augmentation method for Neural Machine Translation (NMT). The main idea is to minimize the vicinal risk over virtual sentences sampled from two …...
Adversarial Self-Supervised Learning for Out-of-Domain Detection
AbstractDetecting out-of-domain (OOD) intents is crucial for the deployed task-oriented dialogue system. Previous unsupervised OOD detection methods only extract discriminative features of different in-domain intents while supervised counterparts can directly …...
Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation
AbstractNeural Machine Translation (NMT) models are known to suffer from noisy inputs. To make models robust, we generate adversarial augmentation samples that attack the model and preserve the source-side meaning …...
Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation
AbstractThough model robustness has been extensively studied in language understanding, the robustness of Seq2Seq generation remains understudied. In this paper, we conduct the first quantitative analysis on the robustness of …...