Alongside increasing use of Machine Translation (MT) in translator workflows, Translation Memory (TM) continues to be a valuable tool providing complementary functionality, and is a technology that has evolved in recent years, in particular with developments around subsegment recall that attempt to leverage more content from TM data than segment-level fuzzy matching. But how fit-for-purpose is ...

Machine Translation (MT) is being deployed for a range of use-cases by millions of people on a daily basis. There should, therefore, be no doubt as to the utility of MT. However, not everyone is convinced that MT can be useful, especially as a productivity enhancer for human translators. In this chapter, I address this issue, describing how MT is currently deployed, how its output is evaluated ...

Abstract Post-editing has become an important part not only of translation research but also in the global industry. While computer-aided tools, such as memories, are considered to be a translator's work, lately, machine (MT) systems have been accepted by human translators. However, many translators still adopting changes brought technologies This paper introduces novel approach for seeking sui...

The present research is a descriptive corpus-based translation study aiming at pinpointing the patterns of translation into Persian when dealing with English Verb Phrase Ellipsis (VPE). After scrutiny of the strategies applied by Persian translators some regular patterns were drawn, with the exception that the observed translation behavior may be taken as advantageous information for improving ...

In the second year of evaluations of the ARPA HLT Machine Translation (MT) Initiative, methodologies developed and tested in 1992 were applied to the 1993 MT test runs. The current methodology optimizes the inherently subjective judgments on translation accuracy and quality by channeling the judgments of non-translators into many data points which reflect both the comparison of the performance ...

Machine translation (MT) is a complex and a difficult task. It is not possible to achieve human competing performance with the present state of technology. Automating the process of translation of natural languages requires a number of knowledge sources and their appropriate invocation in the translation engine. A practical machine translation system with limited resources cannot embody all the...

This paper discusses preliminary work investigating the application of Machine Translation (MT) metrics toward the evaluation of translations written by human novice (student) translators. We describe a study in which we apply the metric TERp (Translation Edit Rate Plus) to a corpus of student-written translations from Spanish to English and compare the judgments of TERp against assessments pro...

In this paper we combine two strands of machine translation (MT) research: automatic postediting (APE) and multi-engine (system combination) MT. APE systems learn a target-languageside second stage MT system from the data produced by human corrected output of a first stage MT system, to improve the output of the first stage MT in what is essentially a sequential MT system combination architectu...

For this term paper in the course Natural Language Processing, NLP1 within GSLT, I have chosen to explore some issues of NLP related to machine translation (MT). The development in MT systems shows that the aim is clearly not to replace human translators but instead to focus on domain-restricted mass-translations and systems for non-translators, new areas enabled by modern information technics....

Along with the growing need for intercultural and translingual communication in an increasingly globalized world, machine translation (MT) becomes more and more important both in assisting language professionals in their daily work and in helping non-professionals understand and create texts in foreign languages. Based on the frequent assumption that it is machine translation's aim to replace h...