Fetching the paper…
Reading the bibliography…
The state of the art of handling rich morphology in neural machine translation (NMT) is to break word forms into subword units, so that the overall vocabulary size of these units fits the practical limits given by the NMT model and GPU memory capacity.
Slavíčková, E.: Retrográdní morfematický slovník češtiny. Academia (1975)
1975
Earlier work this paper cites.
Koehn, P.: Europarl: A Parallel Corpus for Statistical Machine Translation. In: MT Summit. pp. 79–86. AAMT, AAMT, Phuket, Thailand (2005)
2005
Earlier work this paper cites.
Koehn, P., et al.: Moses: Open source toolkit for statistical machine translation. In: ACL Poster and Demonstration Sessions. pp. 177–180 (2007)
2007
Earlier work this paper cites.
Tiedemann, J.: News from OPUS - A collection of multilingual parallel corpora with tools and interfaces. In: RANLP, vol. V, pp. 237–248 (2009)
2009
Earlier work this paper cites.
Hajič, J., Hlaváčová, J.: MorfFlex CZ (2013), http://hdl.handle.net/11858/00-097C-0000-0015-A780-9 , LINDAT/CLARIN dig. library, Charles University
2013
Cited alongside, same era.
Virpioja, S., Smit, P., Grönroos, S.A., Kurimo, M.: Morfessor 2.0: Python implementation and extensions for Morfessor baseline. Tech. rep. (2013), Aalto University publication series SCIENCE + TECHNOLOGY; 25/2013
2013
Cited alongside, same era.
Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: ACL. pp. 1715–1725 (2016)
2016
Cited alongside, same era.
2016
Cited alongside, same era.
2016
Later among the works it cites.
Huck, M., Riess, S., Fraser, A.: Target-side word segmentation strategies for neural machine translation. In: WMT. pp. 56–67. ACL (2017)
2017
Later among the works it cites.
Pinnis, M., Krišlauks, R., Deksne, D., Miks, T.: Neural Machine Translation for Morphologically Rich Languages with Improved Sub-word Units and Synthetic Data, pp. 237–245. Springer International Publishing, Cham (2017)
2017
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…