Character-Aware Decoder for Translation into Morphologically Rich Languages
Abstract
Neural machine translation (NMT) systems operate primarily on words (or sub-words), ignoring lower-level patterns of morphology. We present a character-aware decoder designed to capture such patterns when translating into morphologically rich languages. We achieve character-awareness by augmenting both the softmax and embedding layers of an attention-based encoder-decoder model with convolutional neural networks that operate on the spelling of a word. To investigate performance on a wide variety of morphological phenomena, we translate English into 14 typologically diverse target languages using the TED multi-target dataset. In this low-resource setting, the character-aware decoder provides consistent improvements with BLEU score gains of up to . In addition, we analyze the relationship between the gains obtained and properties of the target language and find evidence that our model does indeed exploit morphological patterns.
Cite
@article{arxiv.1809.02223,
title = {Character-Aware Decoder for Translation into Morphologically Rich Languages},
author = {Adithya Renduchintala and Pamela Shapiro and Kevin Duh and Philipp Koehn},
journal= {arXiv preprint arXiv:1809.02223},
year = {2019}
}
Comments
9 pages (12 including Appendix), 5 figures, Accepted at MT Summit 2019