Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers

Tim Z. Xiao, Aidan Gomez, Yarin Gal

Keywords: Bayesian Deep Learning, Uncertainty, NMT, Transformer

Abstract: We detect out-of-training-distribution sentences in Neural Machine Translation using the Bayesian Deep Learning equivalent of Transformer models. For this we develop a new measure of uncertainty designed specifically for long sequences of discrete random variables—i.e. words in the output sentence. Our new measure of uncertainty solves a major intractability in the naive application of existing approaches on long sentences. We use our new measure on a Transformer model trained with dropout approximate inference. On the task of German-English translation using WMT13 and Europarl, we show that with dropout uncertainty our measure is able to identify when Dutch source sentences, sentences which use the same word types as German, are given to the model instead of German.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: A new measure for estimating uncertainty in NMT.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=rFEpuSmNte