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 language | English |
|---|---|
| Title of host publication | First Conference on Machine Translation (WMT16); Berlin, Germany |
| Publisher | Association for Computational Linguistics |
| Pages | 289-295 |
| Number of pages | 7 |
| ISBN (Electronic) | 978-1-945626-01-2 |
| Publication status | Published - 11 Aug 2016 |
| MoE publication type | A4 Conference publication |
| Event | Conference on Machine Translation - Berlin, Germany Duration: 11 Aug 2016 → 12 Aug 2016 Conference number: 1 |
Conference
| Conference | Conference on Machine Translation |
|---|---|
| Abbreviated title | WMT2016 |
| Country/Territory | Germany |
| City | Berlin |
| Period | 11/08/2016 → 12/08/2016 |
Keywords
- morfessor
- morphological segmentation
- statistical machine translation