The aim of any Automatic Translation project is to give a mechanical procedure for finding an equivalent expression in the target lan6uage for any sentence in the source lan6uage. The aim of any lin6uistic translation project is to find the corresponding structures of the languages dealt with. With both of these aims in mind, the empirical method was adopted in the project described in this paper.

We present a work in progress aimed at extracting translation pairs of source and target dependency treelets to be used in a dependency-basedmachine translation system. We introduce a novel unsupervised method for parallel tree segmentation based on Gibbs sampling. Using the data from a Czech-English parallel treebank, we show that the procedure converges to a dictionary containing reasonably s...

This paper describes LIMSI’s submissions to the Sixth Workshop on Statistical Machine Translation. We report results for the FrenchEnglish and German-English shared translation tasks in both directions. Our systems use n-code, an open source Statistical Machine Translation system based on bilingual n-grams. For the French-English task, we focussed on finding efficient ways to take advantage of ...

This paper gives an overview of the stochastic modelling approach to machine translation. Starting with the Bayes decision rule as in pattern classification and speech recognition, we show how the resulting system architecture can be structured into three parts: the language model probability, the string translation model probability and the search procedure that generates the word sequence in ...

In this article we describe HiFST, a lattice-based decoder for hierarchical phrase-based translation and alignment. The decoder is implemented with standard Weighted Finite-State Transducer (WFST) operations as an alternative to the well-known cube pruning procedure. We find that the use of WFSTs rather than k-best lists requires less pruning in translation search, resulting in fewer search err...

Previous methods on improving translation quality by employing multiple SMT models usually carry out as a secondpass decision procedure on hypotheses from multiple systems using extra features instead of using features in existing models in more depth. In this paper, we propose translation model generalization (TMG), an approach that updates probability feature values for the translation model ...

This paper presents a methodology that aims at the specification, verification and prototyping of large distributed systems. This methodology relies on H-COSTAM : a high level representation that supports hierarchy and focuses on message passing communication mechanisms. In order to enable validation based on a formal representation, a translation procedure to Petri net is proposed. We also sho...

We present a biparsing algorithm for Stochastic Bracketing Inversion Transduction Grammars that runs in O(bn3) time instead of O(n6). Transduction grammars learned via an EM estimation procedure based on this biparsing algorithm are evaluated directly on the translation task, by building a phrase-based statistical MT system on top of the alignments dictated by Viterbi parses under the induced b...

Let P = {p1, p2,..., pn} and Q = {q1, q2,..., qm} be two simple polygons monotonic in directions θ and φ, respectively. It is shown that P and Q are separable with a single translation in at least one of the directions: θ + π / 2, φ + π / 2. Furthermore, a direction for carrying out such a translation can be determined in O(m + n) time. This procedure is of use in solving the FIND-PATH problem ...

  In this article the possible effects of the translation technologies on the critical thinking and translation ability of the students of the Translation Studies would be studied through a pre-experimental method of research. The participants of this research were thirty one Iranian senior Translation Studies students at the age group of 20-26 who were selected based on their age, educational...