1 |
Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation ...
|
|
|
|
Abstract:
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 for this approach is that we cannot decide whether the generated examples are adversarial to the target NMT model or the auxiliary backward one, as the reconstruction error through the RTT can be related to either. To remedy this problem, we propose a new criterion for NMT adversarial examples based on the Doubly Round-Trip Translation (DRTT). Specifically, apart from the source-target-source RTT, we also consider the target-source-target one, which is utilized to pick out the authentic adversarial examples for the target NMT model. Additionally, to enhance the robustness of the NMT model, we introduce the masked language models to construct bilingual adversarial pairs based on DRTT, which are used to train the NMT model directly. Extensive experiments on both the clean and noisy test sets ... : Accepted at NAACL 2022 as a long paper of main conference ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2204.08689 https://arxiv.org/abs/2204.08689
|
|
BASE
|
|
Hide details
|
|
2 |
Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
EAG: Extract and Generate Multi-way Aligned Corpus for Complete Multi-lingual Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Modeling Bilingual Conversational Characteristics for Neural Chat Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Sequence-Level Training for Non-Autoregressive Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Competence-based Curriculum Learning for Multilingual Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|