Learning to Translate with Multiple Objectives
نویسندگان
چکیده
We introduce an approach to optimize a machine translation (MT) system on multiple metrics simultaneously. Different metrics (e.g. BLEU, TER) focus on different aspects of translation quality; our multi-objective approach leverages these diverse aspects to improve overall quality. Our approach is based on the theory of Pareto Optimality. It is simple to implement on top of existing single-objective optimization methods (e.g. MERT, PRO) and outperforms ad hoc alternatives based on linear-combination of metrics. We also discuss the issue of metric tunability and show that our Pareto approach is more effective in incorporating new metrics from MT evaluation for MT optimization.
منابع مشابه
An Investigation on the Relationship between the Grammatical Competence of Young Iranian English Translation Students and their Ability to Translate from English to Farsi
Today, everything has changed and this has brought a need for learning a second language. Most countries across the world use English as their second/foreign language and the fundamental part of this process is grammar, i.e., the combination of sound, structure, and meaning system of language. A sentence can be composed of several words, clauses, as well as grammatical rules. These grammat...
متن کاملAutomated Detection of Multiple Sclerosis Lesions Using Texture-based Features and a Hybrid Classifier
Background: Multiple Sclerosis (MS) is the most frequent non-traumatic neurological disease capable of causing disability in young adults. Detection of MS lesions with magnetic resonance imaging (MRI) is the most common technique. However, manual interpretation of vast amounts of data is often tedious and error-prone. Furthermore, changes in lesions are often subtle and extremely unrepresentati...
متن کاملDifferent Learning Levels in Multiple-choice and Essay Tests: Immediate and Delayed Retention
This study investigated the effects of different learning levels, including Remember an Instance (RI), Remember a Generality (RG), and Use a Generality (UG) in multiple-choice and essay tests on immediate and delayed retention. Three-hundred pre-intermediate students participated in the study. Reading passages with multiple-choice and essay questions in different levels of learning were giv...
متن کاملPrediction of Academic Self-efficacy Based on Self-regulated Learning Strategies, Metacognition Strategies And Goal-Progress Orientation In Students
The purpose of this study was to determine the prediction of academic self-efficacy based on self-regulated learning strategies, metacognition strategies and goal-progress orientation in students of Islamic Azad University branch Ahvaz. This research is correlational. For this purpose, the community of students, 400 people (180 boys and 180 girls) was selected based on stratified random samplin...
متن کاملExploring Language Learning Strategy Use: The Role of Multiple Intelligences, L2 Proficiency and Gender
Multiple intelligences (MI), second/foreign (L2) proficiency and gender are postulated to contribute to language learning strategies (LLS). This study, first, examined whether there was any relationship between Iranian EFL learners’ LLS, on the one hand, and their MI, L2 proficiency, on the other hand. In so doing, it explored the relationship of the overall L2 strategy as well as individual st...
متن کامل