IT is now twelve years since I tentatively suggested that it should be possible to translate a foreign language by means of a digital computer. During this period many people have started to work on the idea, and we have now reached a stage when at least in theory it would be possible to set about building a special purpose translating machine. It may be interesting, therefore, to survey how ta...

1. I N T R O D U C T I O N Despite the long history of machine translation projects, and the well-known effects that evaluations such as the ALPAC Report (Pierce et al., 1966) have had on that history, optimal MT evaluation methodologies remain elusive. This is perhaps due in part to the subjectivity inherent in judging the quality of any translation output (human or machine). The difficulty al...

Statistical Machine Translation is a modern success: Given a source language sentence, SMT finds the most probable target language sentence, based on (1) properties of the source; (2) probabilistic source--target mappings at the level of words, phrases and/or sub-structures; and (3) properties of the target language. SMT translates individual sentences because the search space even for a single...

In the dark ages of machine translation, it is said that researchers at tempted a Direct Approach--word-for-word substitution. But this could not have survived much beyond the first inspection of the output. The most common approach adopted in working machine translation systems is the Transfer Approach illustrated in Figure 1. A text in a source language is analyzed to some depth, producing, f...

We carried out a study in which we explored the feasibility of machine translation for Twitter for the language pair English and German. As a first step we created a small bilingual corpus of 1,000 tweets. Using this corpus we carried out an analysis of the linguistic features of tweets. We tested different strategies of domain adaptation and found that they improved translation performance. In...

We present a probabilistic bilingual capitalization model for capitalizing machine translation outputs using conditional random fields. Experiments carried out on three language pairs and a variety of experiment conditions show that our model significantly outperforms a strong monolingual capitalization model baseline, especially when working with small datasets and/or European language pairs.