Reducing Hallucinations in Neural Machine Translation with Feature Attribution. (arXiv:2211.09878v1 [cs.CL])

Neural conditional language generation models achieve the state-of-the-art in
Neural Machine Translation (NMT) but are highly dependent on the quality of
parallel training dataset. When trained on low-quality datasets, these models
are prone to various error types, including hallucinations, i.e. outputs that
are fluent, but unrelated to the source sentences. These errors are
particularly dangerous, because on the surface the translation can be perceived
as a correct output, especially if the reader does not understand the source
language. We present …

arxiv attribution feature machine machine translation neural machine translation translation