Jacob Eisenstein, Yong Cheng, Lu Jiang, Wolfgang Macherey
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
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-tosequence 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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2006.11834")
get_code_for_paper("2006.11834")
have("2006.11834")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2006.11834.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2006.11834)
Connect an agent — have() is free.