Kriya - The SFU System for Translation Task at WMT-12
نویسندگان
چکیده
This paper describes our submissions for the WMT-12 translation task using Kriya our hierarchical phrase-based system. We submitted systems in French-English and English-Czech language pairs. In addition to the baseline system following the standard MT pipeline, we tried ensemble decoding for French-English. The ensemble decoding method improved the BLEU score by 0.4 points over the baseline in newstest-2011. For English-Czech, we segmented the Czech side of the corpora and trained two different segmented models in addition to our baseline system.
منابع مشابه
Abu-MaTran at WMT 2016 Translation Task: Deep Learning, Morphological Segmentation and Tuning on Character Sequences
This paper presents the systems submitted by the Abu-MaTran project to the Englishto-Finnish language pair at the WMT 2016 news translation task. We applied morphological segmentation and deep learning in order to address (i) the data scarcity problem caused by the lack of in-domain parallel data in the constrained task and (ii) the complex morphology of Finnish. We submitted a neural machine t...
متن کاملUsing Syntactic Coupling Features for Discriminating Phrase-Based Translations (WMT-08 Shared Translation Task)
Our participation in the shared translation task at WMT-08 focusses on news translation from English to French. Our main goal is to contrast a baseline version of the phrase-based MATRAX system, with a version that incorporates syntactic “coupling” features in order to discriminate translations produced by the baseline system. We report results comparing different feature combinations.
متن کاملKriya - An end-to-end Hierarchical Phrase-based MT System
This paper describes Kriya – a new statistical machine translation (SMT) system that uses hierarchical phrases, whichwere first introduced in the Hieromachine translation system (Chiang, 2007). Kriya supports both a grammar extraction module for synchronous context-free grammars (SCFGs) and a CKY-based decoder. There are several re-implementations of Hiero in the machine translation community, ...
متن کاملThe Edinburgh/LMU Hierarchical Machine Translation System for WMT 2016
This paper describes the hierarchical phrase-based machine translation system built jointly by the University of Edinburgh and the University of Munich (LMU) for the shared translation task at the ACL 2016 First Conference on Machine Translation (WMT16). The WMT16 Edinburgh/LMU system was trained for translation of news domain texts from English into Romanian. We participated in the shared task...
متن کاملTerrorCat: a Translation Error Categorization-based MT Quality Metric
We present TerrorCat, a submission to the WMT’12 metrics shared task. TerrorCat uses frequencies of automatically obtained translation error categories as base for pairwise comparison of translation hypotheses, which is in turn used to generate a score for every translation. The metric shows high overall correlation with human judgements on the system level and more modest results on the level ...
متن کامل