SMT typically models translation at the sentence level, ignoring wider document context. Does this hurt the consistency of translated documents? Using a phrase-based SMT system in various data conditions, we show that SMT translates documents remarkably consistently, even without document knowledge. Nevertheless, translation inconsistencies often indicate translation errors. However, unlike in human translation, these errors are rarely due to terminology inconsistency. They are more often symptoms of deeper issues with SMT models instead.Peer reviewed: YesNRC publication: Ye
In this study, we compare the output quality of two MT systems, a statistical (SMT) and a neural (NM...
When parallel or comparable corpora are harvested from the web, there is typically a tradeoff betwee...
Most of the current Machine Translation systems are designed to translate a document sentence by sen...
Coreferences to a German compound (e.g. Nordwand) can be made using its last constituent (e.g. Wand)...
Most of the current SMT systems work at sentence level. They translate a text assuming that sentence...
Term translation is of great importance for statistical machine translation (SMT), es-pecially docum...
Being consistent in technical translations is difficult. Using translation memory software could be ...
Trend I: combining semantics and SMT in attempt to generate not only grammatical but also meaning-p...
Statistical Machine Translation (SMT) is a new paradigm in machine translation, which enables high-q...
Many natural language processes have some degree of preprocessing of data: tokenisation, stemming an...
Many natural language processes have some degree of preprocessing of data: tokenisation, stemming an...
The translation process in statistical machine translation (SMT) is shaped by technical constraints ...
We show for the first time that incorporating the predictions of a word sense disambigua-tion system...
The BLEU scores and translation fluency for the current state-of-the-art SMT systems based on IBM mo...
In cases when phrase-based statistical machine translation (SMT) is applied to languages with rather...
In this study, we compare the output quality of two MT systems, a statistical (SMT) and a neural (NM...
When parallel or comparable corpora are harvested from the web, there is typically a tradeoff betwee...
Most of the current Machine Translation systems are designed to translate a document sentence by sen...
Coreferences to a German compound (e.g. Nordwand) can be made using its last constituent (e.g. Wand)...
Most of the current SMT systems work at sentence level. They translate a text assuming that sentence...
Term translation is of great importance for statistical machine translation (SMT), es-pecially docum...
Being consistent in technical translations is difficult. Using translation memory software could be ...
Trend I: combining semantics and SMT in attempt to generate not only grammatical but also meaning-p...
Statistical Machine Translation (SMT) is a new paradigm in machine translation, which enables high-q...
Many natural language processes have some degree of preprocessing of data: tokenisation, stemming an...
Many natural language processes have some degree of preprocessing of data: tokenisation, stemming an...
The translation process in statistical machine translation (SMT) is shaped by technical constraints ...
We show for the first time that incorporating the predictions of a word sense disambigua-tion system...
The BLEU scores and translation fluency for the current state-of-the-art SMT systems based on IBM mo...
In cases when phrase-based statistical machine translation (SMT) is applied to languages with rather...
In this study, we compare the output quality of two MT systems, a statistical (SMT) and a neural (NM...
When parallel or comparable corpora are harvested from the web, there is typically a tradeoff betwee...
Most of the current Machine Translation systems are designed to translate a document sentence by sen...