The SDL Language Weaver Systems in the WMT12 Quality Estimation Shared Task
نویسندگان
چکیده
We present in this paper the system submissions of the SDL Language Weaver team in the WMT 2012 Quality Estimation shared-task. Our MT quality-prediction systems use machine learning techniques (M5P regression-tree and SVM-regression models) and a feature-selection algorithm that has been designed to directly optimize towards the official metrics used in this shared-task. The resulting submissions placed 1st (the M5P model) and 2nd (the SVM model), respectively, on both the Ranking task and the Scoring task, out of 11 participating teams.
منابع مشابه
PRHLT Submission to the WMT12 Quality Estimation Task
This is a description of the submissions made by the pattern recognition and human language technology group (PRHLT) of the Universitat Politècnica de València to the quality estimation task of the seventh workshop on statistical machine translation (WMT12). We focus on two different issues: how to effectively combine subsequence-level features into sentence-level features, and how to select th...
متن کاملQuality Estimation: an experimental study using unsupervised similarity measures
We present the approach we took for our participation to the WMT12 Quality Estimation Shared Task: our main goal is to achieve reasonably good results without appeal to supervised learning. We have used various similarity measures and also an external resource (Google N -grams). Details of results clarify the interest of such an approach.
متن کاملFindings of the 2012 Workshop on Statistical Machine Translation
This paper presents the results of the WMT12 shared tasks, which included a translation task, a task for machine translation evaluation metrics, and a task for run-time estimation of machine translation quality. We conducted a large-scale manual evaluation of 103 machine translation systems submitted by 34 teams. We used the ranking of these systems to measure how strongly automatic metrics cor...
متن کاملLORIA System for the WMT12 Quality Estimation Shared Task
In this paper we present the system we submitted to the WMT12 shared task on Quality Estimation. Each translated sentence is given a score between 1 and 5. The score is obtained using several numerical or boolean features calculated according to the source and target sentences. We perform a linear regression of the feature space against scores in the range [1:5]. To this end, we use a Support V...
متن کاملLimitations of MT Quality Estimation Supervised Systems: The Tails Prediction Problem
In this paper we address the question of the reliability of the predictions made by MT Quality Estimation (QE) systems. In particular, we show that standard supervised QE systems, usually trained to minimize MAE, make serious mistakes at predicting the quality of the sentences in the tails of the quality range. We describe the problem and propose several experiments to clarify their causes and ...
متن کامل