The translation quality of machine systems depends on the parallel corpus used for training, in particular quantity and corpus. However, building a high-quality large-scale is complex expensive, particularly specific domain Therefore, data augmentation techniques are widely translation. input back-translation method monolingual text, which available from many sources, therefore this can be easi...

In neural interactive translation prediction, a system provides translation suggestions (“auto-complete” functionality) for human translators. These translation suggestions may be rejected by the translator in predictable ways; being able to estimate confidence in the quality of translation suggestions could be useful in providing additional information for users of the system. We show that a v...

We propose a novel statistical translation model to improve translation selection of collocation. In the statistical approach that has been popularly applied for translation selection, bilingual corpora are used to train the translation model. However, there exists a formidable bottleneck in acquiring large-scale bilingual corpora, in particular for language pairs involving Chinese. In this pap...

Compilers or language translators can be generated using a variety of formal specification techniques. Whether generation is worthwhile depends on the effort required to specify the translation task and the quality of the generated compiler. This paper reports the results from a systematic comparison of a hand-coded translator for the Icon programming language with one generated by the Eli comp...

This work presents translation results for the three data sets made available in the shared task “Exploiting Parallel Texts for Statistical Machine Translation” of the HLT-NAACL 2006 Workshop on Statistical Machine Translation. All results presented were generated by using the Ngram-based statistical machine translation system which has been enhanced from the last year’s evaluation with a tagge...

In this paper, we propose a phrase segmentation model for the phrase-based statistical machine translation. We observed that good translation candidates generated by a conventional phrase-based SMT decoder have lexical cohesion and show more uniform translation for each phrase segment. Based on the observation, we propose a novel phrase segmentation model using collocation between two adjacent ...

Collocation translation is important for machine translation and many other NLP tasks. Unlike previous methods using bilingual parallel corpora, this paper presents a new method for acquiring collocation translations by making use of monolingual corpora and linguistic knowledge. First, dependency triples are extracted from Chinese and English corpora with dependency parsers. Then, a dependency ...