@inproceedings{banerjee-bhattacharyya-2018-meaningless,
    title = "Meaningless yet meaningful: Morphology grounded subword-level {NMT}",
    author = "Banerjee, Tamali  and
      Bhattacharyya, Pushpak",
    editor = {Faruqui, Manaal  and
      Sch{\"u}tze, Hinrich  and
      Trancoso, Isabel  and
      Tsvetkov, Yulia  and
      Yaghoobzadeh, Yadollah},
    booktitle = "Proceedings of the Second Workshop on Subword/Character {LE}vel Models",
    month = jun,
    year = "2018",
    address = "New Orleans",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W18-1207/",
    doi = "10.18653/v1/W18-1207",
    pages = "55--60",
    abstract = "We explore the use of two independent subsystems Byte Pair Encoding (BPE) and Morfessor as basic units for subword-level neural machine translation (NMT). We show that, for linguistically distant language-pairs Morfessor-based segmentation algorithm produces significantly better quality translation than BPE. However, for close language-pairs BPE-based subword-NMT may translate better than Morfessor-based subword-NMT. We propose a combined approach of these two segmentation algorithms Morfessor-BPE (M-BPE) which outperforms these two baseline systems in terms of BLEU score. Our results are supported by experiments on three language-pairs: English-Hindi, Bengali-Hindi and English-Bengali."
}