Abstract The Interactive Machine Translation (IMT) systems produce translations combining
the knowledge of professional translators with the generation speed of the Machine …

One major drawback of using Translation Memories (TMs) in phrase-based Machine
Translation (MT) is that only continuous phrases are considered. In contrast, syntax-based …

We report on the results of an experiment aimed at enabling a machine translation system to
select the appropriate strategy for dealing with words and phrases which have different …

Current approaches to Machine Translation (MT) Evaluation are clearly unsatisfactory. Most
of the existing metrics work only at the lexical level, by rewarding n-gram matches between …

Over the last few years, machine translation (MT) has transformed from an academic
research platform into a productivity or gisting tool adopted by several end users. In this talk …

This chapter presents in detail the main translation process of PRESEMT, delving deeper in
the core of the system and its inner workings. All SMT systems (Koehn 2010), which …

Multi-word expressions include a wide list of categories such as idiomatic expressions,
proverbs, collocations, compound words, domain-specific terms, named entities. According …

The performance of machine translation technology after 50 years of development leaves
much to be desired. There is a high demand for well performing and cheap MT systems for …

The European Association for Machine Translation (EAMT) has a long tradition for
organising annual workshops and conferences with the purpose of bringing together people …

The multilingual machine translation system described in the first part of this paper
demonstrates that the translation memory (TM) can be used in a creative way for making the …