The lazy encoder : A fine-grained analysis of the role of morphology in neural machine translation

• Neural sequence-to-sequence models have proven very effective for machine translation, but at the expense of model interpretability. To shed more light into the role played by linguistic structure in the process of neural machine translation, we perform a fine-grained analysis of how various source-side morphological features are captured at different levels of the NMT encoder while varying the target language. Differently from previous work, we find no correlation between the accuracy of source morphology encoding and translation quality. We do find that morphological features are only captured in context and only to the extent that they are directly transferable to the target words. 

Ämnesord

NATURVETENSKAP  -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Language Technology (hsv//eng)

Nyckelord

Computational linguistics

Computer aided language translation

Morphology

Natural language processing systems

Fine-grained analysis

Interpretability

Linguistic structure

Machine translations

Morphological features

Sequence models

Target language

Translation quality

Signal encoding

Publikations- och innehållstyp

ref (ämneskategori)

kon (ämneskategori)