Cognate-aware morphological segmentation for multilingual neural translation

Stig-Arne Grönroos, Sami Virpioja, Mikko Kurimo

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

72 Downloads (Pure)


This article describes the Aalto University entry to the WMT18 News Translation Shared Task. We participate in the multilingual subtrack with a system trained under the constrained condition to translate from English to both Finnish and Estonian. The system is based on the Transformer model. We focus on improving the consistency of morphological segmentation for words that are similar orthographically, semantically, and distributionally; such words include etymological cognates, loan words, and proper names. For this, we introduce Cognate Morfessor, a multilingual variant of the Morfessor method. We show that our approach improves the translation quality particularly for Estonian, which has less resources for training the translation model.
Original languageEnglish
Title of host publicationThird Conference on Machine Translation (WMT18); Brussels, Belgium
Number of pages8
Publication statusPublished - 31 Oct 2018
MoE publication typeA4 Article in a conference publication
EventConference on Machine Translation - Brussels, Belgium
Duration: 31 Oct 20181 Dec 2018
Conference number: 3


ConferenceConference on Machine Translation
Abbreviated titleWMT


  • neural machine translation
  • morphology
  • cognate
  • multilingual

Cite this