Prepositions are hard to translate, because their meaning is often vague, and the choice of the correct preposition is often arbitrary. At the same time, making the correct choice is often critical to the coherence of the output text. In the context of statistical machine translation, this difficulty is enhanced due to the possible long distance between the preposition and the head it modifies,...

Complex Language Models cannot be easily integrated in the first pass decoding of a Statistical Machine Translation system – the decoder queries the LM a very large number of times; the search process in the decoding builds the hypotheses incrementally and cannot make use of LMs that analyze the whole sentence. We present in this paper the Language Computer’s system for WMT06 that employs LMpow...

Great writers help keep a language efficient for discourse of all kinds. In doing so they produce exceptional texts which may defy Statistical Machine Translation by employing uncommon idiom. Such “turns of phrase” can enter into a Nation’s collective memory and form the basis from which compassion and conviction are conveyed during important national discourse. Communities that unite across la...

The current state-of-the-art in machine translation consists of phrase-based statistical machine translation (PB-SMT) [23], an approach which has been used since the late 1990s, evolving from word-based SMT proposed by IBM [5]. These stringbased techniques (which use no linguistic knowledge) seem to have reached their ceiling in terms of translation quality, while there are still a number of li...

This paper examines the effect of paraphrasing noun-noun compounds in statistical machine translation from Swedish to English. The paraphrases are meant to elicit the underlying relationship that holds between the compounding nouns, with the use of prepositional and verb phrases. Though some types of noun-noun compounds are too lexicalized, or have some other qualities that make them unsuitable...

We participated in the IWSLT 2013 Evaluation Campaign for the MT track for two official directions: German↔English. Our system consisted of a reordering module and a statistical machine translation (SMT) module under a pre-ordering SMT framework. We trained the reordering module using three scalable methods in order to utilize training instances as many as possible. The translation quality of o...

In Statistical Machine Translation (SMT), the constraints on word reorderings have a great impact on the set of potential translations that are explored. Notwithstanding computationnal issues, the reordering space of a SMT system needs to be designed with great care: if a larger search space is likely to yield better translations, it may also lead to more decoding errors, because of the added a...

We propose a new approach to recognize objects and scenes in news videos motivated by the availability of large video collections. This approach considers the recognition problem as the translation of visual elements to words. The correspondences between visual elements and words are learned using the methods adapted from statistical machine translation and used to predict words for particular ...

One problem with phrase-based statistical machine translation is the problem of longdistance reordering when translating between languages with different word orders, such as Japanese-English. In this paper, we propose a method of imposing reordering constraints using document-level context. As the documentlevel context, we use noun phrases which significantly occur in context documents contain...

This paper describes the joint submission of the QUAERO project for the German→English translation task of the ACL 2013 Eighth Workshop on Statistical Machine Translation (WMT 2013). The submission was a system combination of the output of four different translation systems provided by RWTH Aachen University, Karlsruhe Institute of Technology (KIT), LIMSI-CNRS and SYSTRAN Software, Inc. The tra...