AdvAug: Robust Adversarial Augmentation for Neural Machine Translation
Autor: | Yong Cheng, Lu Jiang, Wolfgang Macherey, Jacob Eisenstein |
---|---|
Rok vydání: | 2020 |
Předmět: |
Space (punctuation)
FOS: Computer and information sciences Computer Science - Computation and Language Machine translation Computer science Speech recognition 05 social sciences 010501 environmental sciences Translation (geometry) computer.software_genre 01 natural sciences Adversarial system 0502 economics and business Embedding 050207 economics computer Computation and Language (cs.CL) Sentence 0105 earth and related environmental sciences BLEU |
Zdroj: | ACL |
DOI: | 10.48550/arxiv.2006.11834 |
Popis: | In 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 vicinity distributions, of which the crucial one is a novel vicinity distribution for adversarial sentences that describes a smooth interpolated embedding space centered around observed training sentence pairs. We then discuss our approach, AdvAug, to train NMT models using the embeddings of virtual sentences in sequence-to-sequence learning. Experiments on Chinese-English, English-French, and English-German translation benchmarks show that AdvAug achieves significant improvements over the Transformer (up to 4.9 BLEU points), and substantially outperforms other data augmentation techniques (e.g. back-translation) without using extra corpora. Comment: published at ACL2020 |
Databáze: | OpenAIRE |
Externí odkaz: |