Information Technologies and Translation Instrumental Competence

2013 ◽  
Vol 765-767 ◽  
pp. 1303-1306
Author(s):  
Pei Hua Lei
Keyword(s):  
Language Learners ◽  
Real World ◽  
Information Technologies ◽  
Translation System ◽  
Undergraduate Level ◽  
Machine Translation System ◽  
Chinese Texts ◽  
Types Of Information ◽  
Made In ◽  
Instrumental Competence

This paper outlines the types of information technologies applied to translation today and translation sub-competences. A study was made in which students were motivated to participate in building DIY corpus based on a given task and to solve the problems in their former translation. It was found that students instrumental competence was improved in recognizing, evaluating, and utilizing information technologies in solving real translation problems, and that their other translation sub-competences could be acquired when translating a real world task in highly contextualized teaching environment. The purpose of the study is to showcase the necessities of including the revising skills required for online machine translate into instrumental competence of language learners at undergraduate level and the possibilities and limitations of online machine translation system when translating Chinese texts into English.

scholarly journals Cross-lingual text similarity exploiting neural machine translation models

2020 ◽  
pp. 016555152091267 ◽  
Author(s):  
Kazuhiro Seki
Keyword(s):  
Machine Translation ◽  
Learning To Rank ◽  
Translation System ◽  
Text Similarity ◽  
Retrieval Task ◽  
Neural Machine Translation ◽  
Intermediate States ◽  
Machine Translation System ◽  
Cross Lingual ◽  
Types Of Information

This article studies cross-lingual text similarity using neural machine translation models. A straightforward approach based on machine translation is to use translated text so as to make the problem monolingual. Another possible approach is to use intermediate states of machine translation models as recently proposed in the related work, which could avoid propagation of translation errors. We aim at improving both approaches independently and then combine the two types of information, that is, translations and intermediate states, in a learning-to-rank framework to compute cross-lingual text similarity. To evaluate the effectiveness and generalisability of our approach, we conduct empirical experiments on English–Japanese and English–Hindi translation corpora for a cross-lingual sentence retrieval task. It is demonstrated that our approach using translations and intermediate states outperforms other neural network–based approaches and is even comparable with a strong baseline based on a state-of-the-art machine translation system.

scholarly journals Is Translation Symmetric?

2002 ◽  
Vol 37 (4) ◽  
pp. 791-801
Author(s):  
Louis Des Tombe
Keyword(s):  
Machine Translation ◽  
Translation System ◽  
Intuitive Notion ◽  
General Properties ◽  
Machine Translation System ◽  
Mathematical Equivalence ◽  
Made In

Abstract General properties of the translation relation are of interest to translators, translatologists and machine translation system designers. As translation is somehow related to the intuitive notion “equivalence”, one wonders whether it has the properties of strict mathematical equivalence. Symmetry is one of these. The paper starts out with some definitions, so that the question can he treated in a meaningful way. The answer turns out to be positive for “perfect” but negative for “imperfect” translation#x2009;; the latter because of a tendency of translators to “weaken” claims made in texts. This asymmetric aspect of imperfect translation is explained by relating it to a “monotonie” view of the organization of discourse. The paper ends with a description of a machine translation system designed to produce perfect translation, and draws conclusions about machine translation design.

English-Dogri Translation System using MOSES

2016 ◽  
Vol 1 (1) ◽  
pp. 45-49
Author(s):  
Avinash Singh ◽  
Asmeet Kour ◽  
Shubhnandan S. Jamwal
Keyword(s):  
Natural Language Processing ◽  
Machine Translation ◽  
Language Processing ◽  
Statistical Machine Translation ◽  
Translation System ◽  
Parallel Corpus ◽  
English System ◽  
Machine Translation System ◽  
Translation Machine ◽  
Language Pair

The objective behind this paper is to analyze the English-Dogri parallel corpus translation. Machine translation is the translation from one language into another language. Machine translation is the biggest application of the Natural Language Processing (NLP). Moses is statistical machine translation system allow to train translation models for any language pair. We have developed translation system using Statistical based approach which helps in translating English to Dogri and vice versa. The parallel corpus consists of 98,973 sentences. The system gives accuracy of 80% in translating English to Dogri and the system gives accuracy of 87% in translating Dogri to English system.

Sign in / Sign up

Export Citation Format

Share Document