Clara Tump


2018

pdf bib
The Lazy Encoder: A Fine-Grained Analysis of the Role of Morphology in Neural Machine Translation
Arianna Bisazza | Clara Tump
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

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.
Search
Co-authors
Venues