Most of the current Machine Translation systems are designed to translate a document sentence by sentence ignoring discourse information and producing incoherencies in the final translations. In this paper we present some documentlevel-oriented post-processes to improve translations’ coherence and consistency. Incoherences are detected and new partial translations are proposed. The work focuses...

In a Hindi to Bengali transfer based machine translation system the baseline lexical transfer module replaces a Hindi word by its most frequent Bengali translation. Some pronouns in Hindi can have multiple translations in Bengali. The choices of actual translations have big impact on the accessibility of the translated sentence. The list of Hindi pronouns is small and their corresponding Bengal...

This paper reports results from an experiment that was aimed at comparing evaluation metrics for machine translation. Implemented as a workshop at a major conference in 2002, the experiment defined an evaluation task, description of the metrics, as well as test data consisting of human and machine translations of two texts. Several metrics, either applicable by human judges or automated, were u...

Constructing a classifier that distinguishes machine translations from human translations is a promising approach to automatically evaluating machine-translated sentences. We developed a classifier with this approach that distinguishes translations based on word-alignment distributions between source sentences and human/machine translations. We used Support Vector Machines as machinelearning al...

In this paper, we report on an unsupervised greedy-style process for acquiring phrase translations from sentence-aligned parallel corpora. Thanks to innovative selection strategies, this process can acquire multiple translations without size criteria, i.e. phrases can have several translations, can be of any size, and their size is not considered when selecting their translations. Even though t...

The existence of cultural gaps causes problems in translation process and harms the aesthetic aspects of texts. In this paper, it was tried to recognize the factors which cause inconsistency between the style of original lyrics and its translations and also find out which translation strategies increase the rate of this distortion. The framework of the study was translation quality assessment b...

This paper describes the use of a bilingual vector model for the automatic discovery of German translations of English terms. The model is built by analysing co-occurence patterns in a parallel corpus of English and German medical abstracts, a method also used for CrossLingual Information Retrieval. The model generates candidate German translations of English words using the cosine similarity m...

Quasi-alphabetic tree bimorphisms [Steinby and Tîrn uc : Syntax-Directed Translations and Quasi-Alphabetic Tree Bimorphisms. Proc. CIAA, LNCS 4783:265 276, 2007] are reconsidered. It is known that the class of (string) translations de ned by such bimorphisms coincides with the class of syntax-directed translations. This result is extended to a smaller class of tree bimorphisms namely (linear an...

We investigate adaptation of a supervised machine learning model for reranking of query translations to new languages in the context of cross-lingual information retrieval. The model is trained to rerank multiple translations produced by a statistical machine translation system and optimize retrieval quality. The model features do not depend on the source language and thus allow the model to be...