We introduce a new type of transduction grammar that allows for learning of probabilistic phrasal bilexica, leading to a significant improvement in spoken language translation accuracy. The current state-of-the-art in statistical machine translation relies on a complicated and crude pipeline to learn probabilistic phrasal bilexica—the very core of any speech translation system. In this paper, w...

We show that it is possible to automatically detect machine translated text at sentence level from monolingual corpora, using text classification methods. We show further that the accuracy with which a learned classifier can detect text as machine translated is strongly correlated with the translation quality of the machine translation system that generated it. Finally, we offer a generic machi...

Domain adaptation is a key feature in Machine Translation. It generally encompasses terminology, domain and style adaptation, especially for human postediting workflows in Computer Assisted Translation (CAT). With Neural Machine Translation (NMT), we introduce a new notion of domain adaptation that we call “specialization” and which is showing promising results both in the learning speed and in...

This paper addresses a method for customizing an English-to-Korean machine translation system from general domain to patent domain. The customizing method consists of following steps: 1) linguistically studying about characteristics of patent documents, 2) extracting unknown words from large patent documents and constructing large bilingual terminology, 3) extracting and constructing the patent...

English-Thai MT systems are nowadays restricted by incomplete vocabularies and translation knowledge. Users must consequently accept only one translation result that is sometimes semantically divergent or ungrammatical. With the according reason, we propose novel Internet-based translation assistant software in order to facilitate document translation from English to Thai. In this project, we u...

Phrase-based machine translation models have shown to yield better translations than Word-based models, since phrase pairs encode the contextual information that is needed for a more accurate translation. However, many phrase pairs do not encode any relevant context, which means that the translation event encoded in that phrase pair is led by smaller translation events that are independent from...

In the framework of the Tc-Star project, we analyze and propose a combination of two Statistical Machine Translation systems: a phrase-based and an N -gram-based one. The exhaustive analysis includes a comparison of the translation models in terms of efficiency (number of translation units used in the search and computational time) and an examination of the errors in each system’s output. Addit...

The time required for our translation system to handle a sentence of length I is a rapidly growing function of i. We describe here a method for analyzing a sentence into a series of pieces that can be translated sequentially. We show that for sentences with ten or fewer words, it is possible to decrease the translation time by 40% with almost no effect on translation accuracy. We argue that for...

We report the results of our work on automating the transliteration decision of named entities for English to Arabic machine translation. We construct a classification-based framework to automate this decision, evaluate our classifier both in the limited news and the diverse Wikipedia domains, and achieve promising accuracy. Moreover, we demonstrate a reduction of translation error and an impro...

We propose a strategy to support Word Sense Disambiguation (WSD) which is designed specifically for multilingual applications, such as Machine Translation. Co-occurrence information extracted from the translation context, i.e., the set of words which have already been translated, is used to define the order in which disambiguation rules produced by a machine learning algorithm are applied. Expe...