Masked Adversarial Generation for Neural Machine Translation
Attacking Neural Machine Translation models is an inherently combinatorial task on discrete sequences, solved with approximate heuristics. Most methods use the gradient to attack the model on each sample independently. Instead of mechanically applying the gradient, could we learn to produce meaningful adversarial attacks ? In contrast to existing approaches, we learn to attack a model by training an adversarial generator based on a language model. We propose the Masked Adversarial Generation (MAG) model, that learns to perturb the translation model throughout the training process. The experiments show that it improves the robustness of machine translation models, while being faster than competing methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingMachine TranslationTranslationSimilar Papers 제목 키워드 기반
Inference Strategies for Machine Translation with Conditional Masking
Conditional masked language model (CMLM) training has proven successful for non-autoregressive and semi-autoregressive sequence generation tasks, such as machine translation. Given a trained CMLM, however, it is not clea…
Language ModelingLanguage ModellingMachine TranslationTranslationGenerating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation
Generating adversarial examples for Neural Machine Translation (NMT) with single Round-Trip Translation (RTT) has achieved promising results by releasing the meaning-preserving restriction. However, a potential pitfall f…
Machine TranslationNMTTranslationGenerating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation
Generating adversarial examples for Neural Machine Translation (NMT) with single Round-Trip Translation (RTT) has achieved promising results by releasing the meaning-preserving restriction. However, a potential pitfall f…
Machine TranslationNMTTranslationMASS: Masked Sequence to Sequence Pre-training for Language Generation
Pre-training and fine-tuning, e.g., BERT, have achieved great success in language understanding by transferring knowledge from rich-resource pre-training task to the low/zero-resource downstream tasks. Inspired by the su…
Conversational Response GenerationDecoderLanguage ModelingMachine Translation+6AMOM: Adaptive Masking over Masking for Conditional Masked Language Model
Transformer-based autoregressive (AR) methods have achieved appealing performance for varied sequence-to-sequence generation tasks, e.g., neural machine translation, summarization, and code generation, but suffer from lo…
Code GenerationDecoderLanguage ModelingLanguage Modelling+2