The Research on Key Issues of Machine Translation

2014 ◽  
Vol 926-930 ◽  
pp. 2177-2180
Author(s):  
Ying Zhu

Translation is a changing process from one language to another language. There are various kinds of languages in the world, in most cases, people can communicate through translation. In today's rapid development of the computer, it is natural to consider using a computer to help translate. Machine translation refers to the use of computer translation. Machine translation is a combination of interdisciplinary research in mathematics, linguistics, computer science and other disciplines and use a computer to translate a natural source language into another target language. Machine translation includes a number of key steps which are the process of machine translation plays a very important role.

2017 ◽  
Vol 108 (1) ◽  
pp. 257-269 ◽  
Author(s):  
Nasser Zalmout ◽  
Nizar Habash

AbstractTokenization is very helpful for Statistical Machine Translation (SMT), especially when translating from morphologically rich languages. Typically, a single tokenization scheme is applied to the entire source-language text and regardless of the target language. In this paper, we evaluate the hypothesis that SMT performance may benefit from different tokenization schemes for different words within the same text, and also for different target languages. We apply this approach to Arabic as a source language, with five target languages of varying morphological complexity: English, French, Spanish, Russian and Chinese. Our results show that different target languages indeed require different source-language schemes; and a context-variable tokenization scheme can outperform a context-constant scheme with a statistically significant performance enhancement of about 1.4 BLEU points.


2020 ◽  
Vol 4 (1) ◽  
pp. 28
Author(s):  
Anak Agung Inten Mayuni

Puja Tri Sandhya is Hindus prayer known in all countries. The original prayer came in Sanskrit language, but every Hindus believer already translate the prayer into their native language. In 1950, Balinese Hindus used Puja Tri Sandhya to get the recognition from the government allowing Parisada Hindu Dharma Indonesia (PHDI)—the major reform movement and Hindus organization in Indonesia—to translate Puja Tri Sandhya into Indonesian. This translation aimed to make every Hindus believer in Indonesia knows about the meaning of the mantras. Besides Indonesian, Puja Tri Sandhya is also translated into the universal language that 20 percent of the world spoke, English. English is believed to give the best medium to other people who want to learn more about Hindus or simply just curious. As a reminder, in this paper Indonesian will be the source language (SL) and English will be the result of the translation so we shall call it target language (TL). In translation, equivalency will be the point to show if the translation is well translated or not. In their book The Theory and Practice of Translation (1959), Nida and Taber state two kinds of equivalency that the translator can use as their reference they are: formal and dynamic equivalence. Here, Puja Tri Sandhya in Indonesian and English versions will be analyzed using 2 kinds of equivalences by Nida and Taber.


2020 ◽  
Vol 34 (05) ◽  
pp. 8568-8575
Author(s):  
Xing Niu ◽  
Marine Carpuat

This work aims to produce translations that convey source language content at a formality level that is appropriate for a particular audience. Framing this problem as a neural sequence-to-sequence task ideally requires training triplets consisting of a bilingual sentence pair labeled with target language formality. However, in practice, available training examples are limited to English sentence pairs of different styles, and bilingual parallel sentences of unknown formality. We introduce a novel training scheme for multi-task models that automatically generates synthetic training triplets by inferring the missing element on the fly, thus enabling end-to-end training. Comprehensive automatic and human assessments show that our best model outperforms existing models by producing translations that better match desired formality levels while preserving the source meaning.1


2018 ◽  
Vol 6 (3) ◽  
pp. 79-92
Author(s):  
Sahar A. El-Rahman ◽  
Tarek A. El-Shishtawy ◽  
Raafat A. El-Kammar

This article presents a realistic technique for the machine aided translation system. In this technique, the system dictionary is partitioned into a multi-module structure for fast retrieval of Arabic features of English words. Each module is accessed through an interface that includes the necessary morphological rules, which directs the search toward the proper sub-dictionary. Another factor that aids fast retrieval of Arabic features of words is the prediction of the word category, and accesses its sub-dictionary to retrieve the corresponding attributes. The system consists of three main parts, which are the source language analysis, the transfer rules between source language (English) and target language (Arabic), and the generation of the target language. The proposed system is able to translate, some negative forms, demonstrations, and conjunctions, and also adjust nouns, verbs, and adjectives according their attributes. Then, it adds the symptom of Arabic words to generate a correct sentence.


Author(s):  
Sven Tarp

AbstractThis contribution treats the concept of a specialised translation dictionary and argues that this concept is much broader than the traditional vision of a bilingual dictionary going from source language to target language. Based on a methodology developed in the framework of the function theory and using qualitative evidence from existing user research, the contribution then discusses the respective phases and sub-phases of the overall translation process where lexicographically relevant problems and needs may occur. Subsequently, it discusses how these needs could be solved in a complex combination of monolingual and bilingual lexicographical solutions and presents an overall concept of a specialised translation dictionary together with some general principles. Finally, it provides examples of how these principles can be applied in both printed and online dictionaries using already available techniques from information and computer science.


2014 ◽  
Vol 986-987 ◽  
pp. 533-536
Author(s):  
Yu Wei Li

Smart grid could meet the electricity demand against the rapid development of economy and society. The idea to implement smart grid is fully in accordance with the energy developing strategy and it will exert far-reaching impact on the adjustment of energy structure, the sustainable development of society as well as low-carbon economy. Currently, smart grid has attracted wide attention around the world and major countries in the world have been carrying out related researches. This paper describes the background and basic concepts of the smart grid, and takes the United States, European Union and China for example to introduce the development characteristics and typical projects. Besides, this paper analyzes and compares the smart grid in U.S., E.U. and China and gives related suggestions on the key issues of the development of smart grid in China.


Babel ◽  
2004 ◽  
Vol 50 (4) ◽  
pp. 332-345 ◽  
Author(s):  
Chunshen Zhu

Abstract The paper begins with an observation of the paradoxical status of Chinese as a lesstranslated source language but a much-translated target language, and that of Chinese translation studies as a much studied subject in China but a little-noted branch of translation studies in the world. It then analyzes the implications of the two current conceptions of Chinese translation studies: either (1) as a self-contained system of "translation studies in China", with China construed as a geopolitical body; or (2) as an open system of "Chinese language/culture-related translation studies", with the Chinese as a nation, a linguistic and cultural entity in an anthropological sense. It points out that the fi rst, exclusive conception has for too long kept Chinese translation studies from advancing a positive engagement with translation studies in other traditions, encouraging polarization of Chinese and non-Chinese translation studies into two opposite systems; while the second, inclusive conception relates the discipline more closely to other fields of Chinese-related academic study in the world, as well as translation studies in other languages/cultures. As such, Chinese translation studies, alongside an "applied" parallel which is more language-specific and practice-oriented, represents a linguistically medium- and culturally area-restricted branch of Partial Translation Studies under Pure Translation Studies. To substantiate its argument, the paper shows how the two conceptions may have infl uenced the interpretation of the time-honoured tenet of faithfulness-accessibility-elegance in Chinese translation studies for its conceptual sensibility and explanatory power. Résumé L’article commence par souligner le statut paradoxal du chinois, qui est une languesource moins traduite mais une langue-cible frequemment traduite, et dont les etudes de traduction chinoises constituent un sujet frequemment etudie en Chine mais une section peu cotee de la traductologie dans le monde. Il analyse ensuite les implications des deux conceptions actuelles de la traductologie chinoise : soit (1) un systeme independant de traductologie en Chine., la Chine etant consideree comme un organe geopolitique ; soit (2) un systeme ouvert d’etudes de traduction liees a la langue et a la culture chinoises., les Chinois etant une nation, une entite linguistique et culturelle au sens anthropologique du terme. Il montre que la premiere conception exclusive a trop longtemps empeche la traductologie chinoise d’avancer un engagement positif avec les etudes de traduction dans d’autres traditions, en encourageant la polarisation de la traductologie chinoise et nonchinoise en deux systemes opposes ; tandis que la seconde conception inclusive rapproche la discipline plus etroitement d’autres domaines d’etudes academiques liees au chinois dans le monde, ainsi que des autres etudes de traduction dans d’autres langues et cultures. En tant que telle, la traductologie chinoise, a cote d’un parallele .applique. qui est plus specifique a la langue et oriente vers la pratique, represente un moyen linguistique et une branche culturellement limitee a un domaine d’etudes partielles de traduction dans les etudes de traduction pures. Pour etayer son argument, l’article montre comment les deux conceptions peuvent avoir influence l’interpretation du principe, consacre par l’usage, de la fidelite — accessibilite — elegance dans la traductologie chinoise pour sa sensibilite conceptuelle et son pouvoir explicatif.


2020 ◽  
Vol 2 (4) ◽  
pp. 28
Author(s):  
. Zeeshan

Machine Translation (MT) is used for giving a translation from a source language to a target language. Machine translation simply translates text or speech from one language to another language, but this process is not sufficient to give the perfect translation of a text due to the requirement of identification of whole expressions and their direct counterparts. Neural Machine Translation (NMT) is one of the most standard machine translation methods, which has made great progress in the recent years especially in non-universal languages. However, local language translation software for other foreign languages is limited and needs improving. In this paper, the Chinese language is translated to the Urdu language with the help of Open Neural Machine Translation (OpenNMT) in Deep Learning. Firstly, a Chineseto Urdu language sentences datasets were established and supported with Seven million sentences. After that, these datasets were trained by using the Open Neural Machine Translation (OpenNMT) method. At the final stage, the translation was compared to the desired translation with the help of the Bleu Score Method.


Author(s):  
VELISLAVA STOYKOVA ◽  
DANIELA MAJCHRAKOVA

The paper presents results of the application of a statistical approach for Slovak to Bulgarian language machine translation. It uses Information Retrieval inspired search techniques and employs sever alalgorithmic steps of parallel statistical search with query expansion in Slovak-Bulgarian EUROPARL 7 Corpus using the Sketch Engine software and its scoring. The search includes the generation of concordances,collocations, word sketch differences, word sketches, and thesauri of the studied keyword (query) by using a statistical scoring, which is regarded as intermediate (inter-lingual) semantic standard presentation by means of which the studied keyword (from the source language) is mapped together with its possible translation equivalents (onto the target language. The results present the study of adjectival collocabillity in both Slovak and Bulgarian language from the corpus of political speech texts outlining the standard semantic relations based on the evaluation of statistical scoring. Finally, the advantages and shortcomings of the approach are discussed.


2020 ◽  
Vol 21 (3) ◽  
Author(s):  
Benyamin Ahmadnia ◽  
Bonnie J. Dorr ◽  
Parisa Kordjamshidi

Neural Machine Translation (NMT) systems require a massive amount of Maintaining semantic relations between words during the translation process yields more accurate target-language output from Neural Machine Translation (NMT). Although difficult to achieve from training data alone, it is possible to leverage Knowledge Graphs (KGs) to retain source-language semantic relations in the corresponding target-language translation. The core idea is to use KG entity relations as embedding constraints to improve the mapping from source to target. This paper describes two embedding constraints, both of which employ Entity Linking (EL)---assigning a unique identity to entities---to associate words in training sentences with those in the KG: (1) a monolingual embedding constraint that supports an enhanced semantic representation of the source words through access to relations between entities in a KG; and (2) a bilingual embedding constraint that forces entity relations in the source-language to be carried over to the corresponding entities in the target-language translation. The method is evaluated for English-Spanish translation exploiting Freebase as a source of knowledge. Our experimental results show that exploiting KG information not only decreases the number of unknown words in the translation but also improves translation quality.


Sign in / Sign up

Export Citation Format

Share Document