Title: Mitigating the Problems of SMT using EBMT
Abstract: Statistical Machine Translation (SMT) typically has difficulties with less-resourced languages, even with homogeneous data. In this report we address the application of Example-Based Machine Translation (EBMT) methods to overcome some of these difficulties. We adopt three alternative approaches to tackle these problems focusing on two poorly resourced translation tasks (English--Bangla and English--Turkish). First, we adopt a runtime approach to EBMT using proportional analogy. In addition to the translation task, we have tested the EBMT system using proportional analogy for named entity transliteration. In the second attempt, we use a compiled approach to EBMT. Finally, we present a novel way of integrating Translation Memory into an EBMT system. We discuss the development of these three different EBMT systems and the experiments we have performed. In addition, we present an approach to augment the output quality by strategically combining EBMT and SMT systems. We also detail the continued work we intend to do for effective hybridization of the pair of systems.