Hybrid Morphological Segmentation for Phrase-Based Machine Translation

Stig-Arne Grönroos, Sami Virpioja, Mikko Kurimo

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

Abstract

This article describes the Aalto University entry to the English-to-Finnish news translation shared task in WMT 2016. Our segmentation method combines the strengths of rule-based and unsupervised morphology. We also attempt to correct errors in the boundary markings by post-processing with a neural morph boundary predictor.
Original languageEnglish
Title of host publicationFirst Conference on Machine Translation (WMT16); Berlin, Germany
PublisherAssociation for Computational Linguistics
Pages289-295
Number of pages7
ISBN (Electronic)978-1-945626-01-2
Publication statusPublished - 11 Aug 2016
MoE publication typeA4 Conference publication
EventConference on Machine Translation - Berlin, Germany
Duration: 11 Aug 201612 Aug 2016
Conference number: 1

Conference

ConferenceConference on Machine Translation
Abbreviated titleWMT2016
Country/TerritoryGermany
CityBerlin
Period11/08/201612/08/2016

Keywords

  • morfessor
  • morphological segmentation
  • statistical machine translation

Fingerprint

Dive into the research topics of 'Hybrid Morphological Segmentation for Phrase-Based Machine Translation'. Together they form a unique fingerprint.
  • Science-IT

    Hakala, M. (Manager)

    School of Science

    Facility/equipment: Facility

Cite this