We report results from a domain adaptation task for statistical machine translation (SMT) using cache-based adaptive language and translation models. We apply an exponential decay factor and integrate the cache models in a standard phrasebased SMT decoder. Without the need for any domain-specific resources we obtain a 2.6% relative improvement on average in BLEU scores using our dynamic adaptat...

This paper gives a detailed analysis of different approaches to adapt a statistical machine translation system towards a target domain using small amounts of parallel in-domain data. Therefore, we investigate the differences between the approaches addressing adaptation on the two main steps of building a translation model: The candidate selection and the phrase scoring. For the latter step we c...

We present a novel online learning approach for statistical machine translation tailored to the computer assisted translation scenario. With the introduction of a simple online feature, we are able to adapt the translation model on the fly to the corrections made by the translators. Additionally, we do online adaption of the feature weights with a large margin algorithm. Our results show that o...

In this paper, we present SAIC’s hybrid machine translation (MT) system and show how it was adapted to the needs of our customer – a major global fashion company. The adaptation was performed in two ways: off-line selection of domain-relevant parallel and monolingual data from a background database, as well as on-line incremental adaptation with customer parallel and translation memory data. Th...

Language modeling is an important part for both speech recognition and machine translation systems. Adaptation has been successfully applied to language models for speech recognition. In this paper we present experiments concerning language model adaptation for statistical machine translation. We develop a method to adapt language models using information retrieval methods. The adapted language...

In this paper, we propose a new domain adaptation technique for neural machine translation called cost weighting, which is appropriate for adaptation scenarios in which a small in-domain data set and a large general-domain data set are available. Cost weighting incorporates a domain classifier into the neural machine translation training algorithm, using features derived from the encoder repres...

Changes in neuronal spontaneous activities after prolonged optic flow stimulation (using the three basic flow modes: translation, radiation and rotation) were inve stigated by extracellular single-unit recording in cortical area PMLS of the cat. The results showed that the evoked responses decreased with the prolongation of visual stimuli, and the spontaneous activities usually dropped to a low...

In Statistical Machine Translation, in-domain and out-of-domain training data are not always clearly delineated. This paper investigates how we can still use mixture-modeling techniques for domain adaptation in such cases. We apply unsupervised clustering methods to split the original training set, and then use mixture-modeling techniques to build a model adapted to a given target domain. We sh...