We use referential translation machines (RTMs) for predicting translation performance. RTMs pioneer a language independent approach to all similarity tasks and remove the need to access any task or domain specific information or resource. We improve our RTM models with the ParFDA instance selection model (Bicici et al., 2015), with additional features for predicting the translation performance, and with improved learning models. We develop RTM models for each WMT15 QET (QET15) subtask and obtain improvements over QET14 results.
RTMs achieve top performance in QET15 ranking 1st in document- and sentence-level prediction tasks and 2nd in word-level prediction task.
This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:
Science Foundation Ireland as part of the ADAPT research center (www.adaptcentre.ie, 07/CE/I1142) at Dublin City University, SFI for the project “Monolingual and Bilingual Text Quality Judgments with Translation Performance Prediction” (computing.dcu.ie/ ˜ebicici/Projects/TIDA_RTM.html, 13/TIDA/I2740)
ID Code:
20882
Deposited On:
29 Oct 2015 12:06 by
Mehmet Ergun Bicici
. Last Modified 22 Jul 2019 14:09