@InProceedings{kunchukuttan-bhattacharyya:2017:SCLeM,
  author    = {Kunchukuttan, Anoop  and  Bhattacharyya, Pushpak},
  title     = {Learning variable length units for SMT between related languages via Byte Pair Encoding},
  booktitle = {Proceedings of the First Workshop on Subword and Character Level Models in NLP},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {14--24},
  abstract  = {We explore the use of segments learnt using Byte Pair Encoding (referred to as
	BPE units) as basic units for statistical machine translation between related
	languages and compare it with orthographic syllables, which are currently the
	best performing basic units for this translation task. BPE identifies the most
	frequent character sequences as basic units, while orthographic syllables are
	linguistically motivated pseudo-syllables. We show that BPE units modestly
	outperform orthographic syllables as units of translation, showing up to 11%
	increase in BLEU score. While orthographic syllables can be used only for
	languages whose writing systems use vowel representations, BPE is writing
	system independent and we show that BPE outperforms other units for non-vowel
	writing systems too. Our results are supported by extensive experimentation
	spanning multiple language families and writing systems.},
  url       = {http://www.aclweb.org/anthology/W17-4102}
}