Machine Translation Systems Athanasios Tryferidis Electrical and Computer Engineer, MLS SA, Greece

2008 ◽  
pp. 211-220
Author(s):  
Athanasios Tryferidis ◽  
Theofanis Korlos
Keyword(s):  
Natural Language ◽  
Machine Translation ◽  
Computational Linguistics ◽  
European Association ◽  
Computer Software ◽  
Linguistic Typology ◽  
Simple Substitution ◽  
Translation Systems ◽  
Basic Level

Machine translation, sometimes referred to by the acronym MT, is a subfield of computational linguistics that investigates the use of computer software to translate text or speech from one natural language to another. At its basic level, MT is performed as a simple substitution of atomic words in one natural language for words in another. Using corpus techniques, more complex translations may be attempted, allowing for better handling of differences in linguistic typology, phrase recognition, and translation of idioms, as well as the isolation of anomalies (Mitkov, 2003). The European Association for Machine Translation (EAMT) defines machine translation (MT) as “the application of computers to the task of translating texts from one natural language to another.”

scholarly journals Approaches to Machine Translation: A Review

2016 ◽  
Vol 1 (1) ◽  
Author(s):  
John Oladosu ◽  
Adebimpe Esan ◽  
Ibrahim Adeyanju ◽  
Benjamin Adegoke ◽  
Olatayo Olaniyan ◽  
...  
Keyword(s):  
Natural Language ◽  
Machine Translation ◽  
Computational Linguistics ◽  
Hybrid Approach ◽  
Computer Software ◽  
The Other ◽  
Information Inequalities ◽  
Satisfactory Performance ◽  
Translation Systems ◽  
Single Approach

Translation is the transfer of the meaning of a text from one language to another. It is a means of sharing information across languages and therefore essential for addressing information inequalities. The work of translation was originally carried out by human translators and its limitations led to the development of machine translators. Machine Translation is a subfield of computational linguistics that investigates the use of computer software to translate text or speech from one natural language to another. There are different approaches to machine translation. This paper reviews the two major approaches (single vs. hybrid) to machine translation and provides critique of existing machine translation systems with their merits and demerits. Several application areas of machine translation and various methods used in evaluating them were also discussed. Our conclusion from the reviewed literatures is that a single approach to machine translation fails to achieve satisfactory performance resulting in lower quality and fluency of the output. On the other hand, a hybrid approach combines the strength of two or more approaches to improve the overall quality and fluency of the translation.

scholarly journals COMPARISON OF PARSING METHODS FOR THE ANALISYS OF A NATURAL LANGUAGE SENTENCE

2021 ◽  
Vol 10 (34) ◽  
Author(s):  
A.N SAK ◽  
◽  
E.V BESSONOVA ◽  
Keyword(s):  
Neural Networks ◽  
Natural Language ◽  
Machine Translation ◽  
Convolutional Neural Networks ◽  
Object Oriented ◽  
Important Task ◽  
Object Oriented Programming ◽  
Parts Of Speech ◽  
Translation Systems

When constructing machine translation systems, an important task is to represent data using graphs, where words act as vertices, and relations between words in a sentence act as edges. One of these tasks at the first stage of the analysis is the classification of words as parts of speech, and at the next stage of the analysis to determine the belonging of words to the sentence members’ classes. The article discusses methods of parsing both on the basis of rules determined in advance by means of traditional object-oriented programming, and on the basis of analysis by means of graph convolutional neural networks with their subsequent training. Online dictionaries act as a thesaurus.

scholarly journals Bodo to English Machine Translation through Transliteration

2019 ◽  
Vol 8 (12) ◽  
pp. 4825-4830
Keyword(s):  
Natural Language ◽  
Machine Translation ◽  
Computational Linguistics ◽  
Language Processing ◽  
Research Work ◽  
Primary Objective ◽  
Target Language ◽  
Translation System ◽  
Hybrid Technique ◽  
High Resource

Machine Translation (MT) is a technique that automatically translates text from one natural language to another using machine like computer. Machine Transliteration (MTn) is also a technique that converts the script of text from source language to target language without changing the pronunciation of the source text. Both the MT and MTn are the challenging research task in the field of Natural Language Processing (NLP) and Computational Linguistics (CL) globally. English is a high resource natural language, whereas Bodo is a low resource natural language. Though Bodo is a recognized language of India; still not much research work has been done on MT and MTn systems due to the low resources. The primary objective of this paper is to develop Bodo to English Machine Translation system with the help of Bodo to English Machine Transliteration system. The Bodo to English MT system has been developed using the Phrase-based Statistical Machine Translation technique for General and News domains of Bodo-English parallel text corpus. The Bodo to English MTn system has been developed using the Hybrid technique for General and News domains of Bodo-English parallel transliterated words/terms. The translation accuracy of the MT system has been evaluated using BLEU technique

scholarly journals Machine Translation System for the Industry Domain and Croatian Language

2020 ◽  
Vol 44 (1) ◽  
pp. 33-50
Author(s):  
Ivan Dunđer
Keyword(s):  
Machine Translation ◽  
Computational Linguistics ◽  
Technology Development ◽  
Domain Adaptation ◽  
Statistical Machine Translation ◽  
Translation System ◽  
Domain Specific ◽  
Extensive Evaluation ◽  
Machine Translation System ◽  
Translation Systems

Machine translation is increasingly becoming a hot research topic in information and communication sciences, computer science and computational linguistics, due to the fact that it enables communication and transferring of meaning across different languages. As the Croatian language can be considered low-resourced in terms of available services and technology, development of new domain-specific machine translation systems is important, especially due to raised interest and needs of industry, academia and everyday users. Machine translation is not perfect, but it is crucial to assure acceptable quality, which is purpose-dependent. In this research, different statistical machine translation systems were built – but one system utilized domain adaptation in particular, with the intention of boosting the output of machine translation. Afterwards, extensive evaluation has been performed – in form of applying several automatic quality metrics and human evaluation with focus on various aspects. Evaluation is done in order to assess the quality of specific machine-translated text.

scholarly journals Dialog between a Lexicographer and a Translator

2015 ◽  
pp. 13-23
Author(s):  
Mark Kit ◽  
Violetta Koseska-Toszewa
Keyword(s):  
Natural Language ◽  
Machine Translation ◽  
Computational Linguistics ◽  
Corpus Linguistics ◽  
Interdisciplinary Approach ◽  
Natural Language Semantics ◽  
Language Semantics

Dialog between a Lexicographer and a TranslatorThe discussion between the authors of the paper concerns the most pressing issues encountered in natural language semantics, as well as in corpus linguistics and computational linguistics. A broad range of knowledge, allowing linguists and information scientists to work together, is required in these areas. The paper describes some primary problems of human and machine translation caused by gaps between different fields of knowledge. The authors suggest that interdisciplinary approach is required when it comes to contrastive studies in linguistics.

Deep Learning

2018 ◽  
Author(s):  
Kyunghyun Cho
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Computational Linguistics ◽  
Language Processing ◽  
Document Classification ◽  
Context Modelling ◽  
Language Modelling

Deep learning has rapidly gained huge popularity among researchers in natural-language processing and computational linguistics in recent years. This chapter gives a comprehensive and detailed overview of recent deep-learning-based approaches to challenging problems in natural-language processing, specifically focusing on document classification, language modelling, and machine translation. At the end of the chapter, new opportunities in natural-language processing made possible by deep learning are discussed, which are multilingual and larger-context modelling.

scholarly journals AN OVERVIEW OF AUTOMATED TRANSLATION AND ITS LINGUISTIC PROBLEMS

2021 ◽  
pp. 139-149
Keyword(s):  
Natural Language ◽  
Machine Translation ◽  
Computational Linguistics ◽  
Language Processing ◽  
Information Exchange ◽  
Rapid Development ◽  
Language Translation ◽  
Target Language ◽  
Technical Documentation ◽  
Automated Translation

Language, as the information carrier, has become the most significant means for humans to communicate. However, it has been considered as the barrier of communications between people from different countries. The problem of converting a language quickly and efficiently has become a problem of common concern for humanity. In fact, the demand for language translation has greatly increased in recent times due to effect of cross-regional communication and the need for information exchange. Most material needs to be translated, including scientific and technical documentation, instruction manuals, legal documents, textbooks, publicity leaflets, newspaper reports, etc. The issue is challenging and difficult but mostly it is tedious and repetitive and requires consistency and accuracy. It is becoming difficult for professional translators to meet the increasing demands of translation. In such a situation, the machine translation can be used as a substitute. Machine Translation is the process of converting a natural source language into another natural target language by computer. It is a branch of natural language processing and it has a close relationship with computational linguistics and natural language understanding. With the rapid development of the Internet and the integration of the world economy, how to overcome the barrier of language has become a common problem of the international community. This paper offers an overview of Machine Translation (MT) including the history of MT, linguistic problems of MT, the problem of multiple meanings in MT, syntactic transformations in MT, translation of phraseological combinations in MT systems.

scholarly journals Modern Machine Translation Systems: Trends and Prospects

2021 ◽  
pp. 41-52
Author(s):  
Oleg Kuzmin ◽  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
Economic Benefits ◽  
Modern World ◽  
Semantic Features ◽  
Translation Systems ◽  
Modern Machine

The modern world is moving towards global digitalization and accelerated software development with a clear tendency to replace human resources by digital services or programs that imitate the doing of similar tasks. There is no doubt that, long term, the use of such technologies has economic benefits for enterprises and companies. Despite this, however, the quality of the final result is often less than satisfactory, and machine translation systems are no exception, as editing of texts translated by using online translation services is still a demanding task. At the moment, producing high-quality translations using only machine translation systems remains impossible for multiple reasons, the main of which lies in the mysteries of natural language: the existence of sublanguages, abstract words, polysemy, etc. Since improving the quality of machine translation systems is one of the priorities of natural language processing (NLP), this article describes current trends in developing modern machine translation systems as well as the latest advances in the field of natural language processing (NLP) and gives suggestions about software innovations that would minimize the number of errors. Even though recent years have seen a significant breakthrough in the speed of information analysis, in all probability, this will not be a priority issue in the future. The main criteria for evaluating the quality of translated texts will be the semantic coherence of these texts and the semantic accuracy of the lexical material used. To improve machine translation systems, we should introduce elements of data differentiation and personalization of information for individual users and their tasks, employing the method of thematic modeling for determining the subject area of a particular text. Currently, there are algorithms based on deep learning that are able to perform these tasks. However, the process of identifying unique lexical units requires a more detailed linguistic description of their semantic features. The parsing methods that will be used in analyzing texts should also provide for the possibility of clustering by sublanguages. Creating automated electronic dictionaries for specific fields of professional knowledge will help improve the quality of machine translation systems. Notably, to date there have been no successful projects of creating dictionaries for machine translation systems for specific sub-languages. Thus, there is a need to develop such dictionaries and to integrate them into existing online translation systems.

scholarly journals A Review of Machine Translation for South Asian Low Resource Languages

2021 ◽  
Vol 12 (5) ◽  
pp. 1134-1147
Author(s):  
Syed Abdul Basit Andrabi, Et. al.
Keyword(s):  
Natural Language ◽  
Programming Languages ◽  
Machine Translation ◽  
Language Processing ◽  
Statistical Machine Translation ◽  
Automatic Generation ◽  
Natural Languages ◽  
Native Languages ◽  
Present Information ◽  
Translation Systems

Machine translation is an application of natural language processing. Humans use native languages to communicate with one another, whereas programming languages communicate between humans and computers. NLP is the field that involves a broad set of techniques for analysis, manipulation and automatic generation of human languages or natural languages with the help of computers. It is essential to provide access to information to people for their development in the present information age. It is necessary to put equal emphasis on removing the barrier of language between different divisions of society. The area of NLP strives to fill this gap of the language barrier by applying machine translation. One natural language is transformed into another natural language with the aid of computers. The first few years of this area were dedicated to the development of rule-based systems. Still, later on, due to the increase in computational power, there was a transition towards statistical machine translation. The motive of machine translation is that the meaning of the translated text should be preserved during translation. This research paper aims to analyse the machine translation approaches used for resource-poor languages and determine the needs and challenges the researchers face. This paper also reviews the machine translation systems that are available for poor research languages.

scholarly journals Extracting Parallel Sentences from Nonparallel Corpora Using Parallel Hierarchical Attention Network

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Shaolin Zhu ◽  
Yong Yang ◽  
Chun Xu
Keyword(s):  
Neural Network ◽  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
State Of The Art ◽  
Research Problem ◽  
Shared Task ◽  
Translation Systems

Collecting parallel sentences from nonparallel data is a long-standing natural language processing research problem. In particular, parallel training sentences are very important for the quality of machine translation systems. While many existing methods have shown encouraging results, they cannot learn various alignment weights in parallel sentences. To address this issue, we propose a novel parallel hierarchical attention neural network which encodes monolingual sentences versus bilingual sentences and construct a classifier to extract parallel sentences. In particular, our attention mechanism structure can learn different alignment weights of words in parallel sentences. Experimental results show that our model can obtain state-of-the-art performance on the English-French, English-German, and English-Chinese dataset of BUCC 2017 shared task about parallel sentences’ extraction.

Sign in / Sign up

Export Citation Format

Share Document