Machine Translation. Can you imagine working as a translator without the help of computer?

Slides:



Advertisements
Similar presentations
TrAva – a tool for evaluating Machine Translation – pedagogical and research possibilities Belinda Maia, Diana Santos, Luís Sarmento & Anabela Barreiro.
Advertisements

Using OLIF, The Open Lexicon Interchange Format Susan McCormick OLIF2 Consortium October 1, 2004.
Criteria for quality assessment of medical information resources EAHIL Workshop Alghero June 7 - 9, 2001 Marie Monik Christine Wickman Karolinska Institutet.
Let’s Write a Haiku By Martha Chapman
The Internet.
EPrints 2.0 / March 4 th 2002 / Glasgow / Chris Gutteridge Introduction to EPrints 2.0 March 4 th 2002 Glasgow Christopher Gutteridge from the Department.
Accessibility issues - The use of Styles in Word Although it has been possible to apply Styles to Word documents since Word 2000 many people still choose.
Read&Write (v7) GOLD A literacy aid for everyone with learning disabilities / difficulties.
Machine Translation II How MT works Modes of use.
Introduction to Computational Linguistics
Unlock the books with IntelligentCAPTURE Xavier Baumgartner University of St. Gallen.
How to Use a Translation Memory Prof. Reima Al-Jarf King Saud University, Riyadh, Saudi Arabia Homepage:
Computational Paradigms in the Humanities – eHumanities and their role and impact in transdisciplinary research Gerhard Budin University of Vienna.
Introducing COMPARA The Portuguese-English Parallel Corpus Ana Frankenberg-Garcia ISLA, Lisbon & Diana Santos SINTEF, Oslo.
FLUP - Elena Zagar Galvão Faculdade de Letras da Universidade do Porto INFORMÁTICA DE TRADUÇÃO FALL SEMESTER 2008 Lesson December 2009 Teacher: Elena.
Where do we stand? Harold Somers Centre for Computational Linguistics, UMIST, Manchester, England Panel session, MT Summit VIII, September 2001.
A Syntactic Translation Memory Vincent Vandeghinste Centre for Computational Linguistics K.U.Leuven
Machine Translation (Level 2) Anna Sågvall Hein GSLT Course, September 2004.
April 2004 TM RASMAT 2004 – Uppsala Business Needs and Practices Pierre-Yves Foucou CTO - SYSTRAN.
What is the Internet? Internet: The Internet, in simplest terms, is the large group of millions of computers around the world that are all connected to.
Machine Translation Anna Sågvall Hein Mösg F
ADMINISTRATION Sources of Information REVISION – BLOCK 6.
Localization and Translation Curriculum for Heritage Speakers "Teaching the Speakers: Heritage Language Learners and the Classroom" Lonny Harrison Texas.
Language Translators By: Henry Zaremba. Origins of Translator Technology ▫1954- IBM gives a demo of a translation program called the “Georgetown-IBM experiment”
An innovative platform to allow translation and indexing of internet sites Localization World
MACHINE TRANSLATION TRANSLATION(5) LECTURE[1-1] Eman Baghlaf.
Machine Translation (MT) By Samar Turkistani Ebtehal al-zahrani Abeer al-rashidi Hanan al- amri Hadeel Morad.
1 Unit 7 Computer-aided Translation. 2 MT and CAT  Human-aided Machine Translation (HAMT)  The machine (the computer) plays the central role in translation.
Researches on Japanese- Chinese/Chinese-Japanese Machine Translation Systems CHEN Jiajun Department of Computer Science&technology Nanjing University
MACHINE TRANSLATION A precious key to communicate beyond linguistic barriers 1.
COMPONENTS OF AN EFFECTIVE WRITING PROGRAM
Russell Taylor. Introduction This Intermediate 1 level Unit is about Programming in High-level Languages In this Unit you will: Identify the requirements.
Machine Translation Dr. Radhika Mamidi. What is Machine Translation? A sub-field of computational linguistics It investigates the use of computer software.
The Internet COM 366 Web Design & Production. Brief history Internet began as nationwide network for Department of Defense in 1960s –Expanded to universities.
FLAVIUS Presentation of Softissimo WP1 Project Management.
Additional Materials1 Other Languages C and C++: Languages used by Systems Programmers. Heavy use by Computer Scientists. COBOL: An ancient Business oriented.
Supervisor: Dr. Eddie Jones Electronic Engineering Department Final Year Project 2008/09 Development of a Speaker Recognition/Verification System for Security.
Week 9: resources for globalisation Finish spell checkers Machine Translation (MT) The ‘decoding’ paradigm Ambiguity Translation models Interlingua and.
Language Services Industry 华豫江 John Hua.
CapturaTalk4Android Demonstration Abi James
Globalisation and machine translation Machine Translation (MT) The ‘decoding’ paradigm Ambiguity Translation models Interlingua and First Order Predicate.
Can Controlled Language Rules increase the value of MT? Fred Hollowood & Johann Rotourier Symantec Dublin.
Their huge range make Ectaco the company to try for the harder to find languages and operating systems. Travellers often choose Ectaco software because.
TRANSLATION & THE HIGH TECH INDUSTRY. INTRODUCTION Translation has been existing ever since mythology began, passed the prophethood, and now in modern.
The End of the World for Translation as We Knew It? © Jost
Evolution of Machine Translation: systems and use John Hutchins [ homepages/WJHutchins] [
READING AND WRITING SOFTWARE Understanding the Tools.
United Nations - UN Translation services Organisational structure Resources.
United Nations - UN Translation services Organisational structure Resources.
October 2005CSA3180 NLP1 CSA3180 Natural Language Processing Introduction and Course Overview.
Computational Linguistics. The Subject Computational Linguistics is a branch of linguistics that concerns with the statistical and rule-based natural.
Machine Translation (Level 2) Anna Sågvall Hein GSLT Course, January 2003.
Auckland 2012Kilgarriff: NLP and Corpus Processing1 The contribution of NLP: corpus processing.
English- language editing for the Latvian EU Council Presidency Aidan McCartney European Parliament Editing Unit.
Introduction to the European Union. The European Union Foundation Purpose.
Luis Avila Tics. We have to recognize all the operating systems we have nowadays in the different smartphones Blackberry: Bb OS Iphone: iOS Nokia: symbian.
Language Technologies Capability Demonstration Alon Lavie, Lori Levin, Alex Waibel Language Technologies Institute Carnegie Mellon University CATANAL Planning.
A Simple English-to-Punjabi Translation System By : Shailendra Singh.
#APMP2016. Submitting proposals in more than one language: a survival guide Considering language and translation as a key component of your value proposition.
English-Lithuanian-English Lexicon Database Management System for MT Gintaras Barisevicius and Elvinas Cernys Kaunas University of Technology, Department.
How can speech technology be used to help people with disabilities?
TYPES OF TRANSLATION.
English-Korean Machine Translation System
How to teach translation technologies
CAT TOOLS.
Translation within the federal government House of Commons Standing Committee on Official Languages April 11, 2016
Google translate app demo
LACONEC A Large-scale Multilingual Semantics-based Dictionary
Technical translation
„Translation is the expression in another language (or target language of what has been expressed in another, source language, preserving semantic and.
Presentation transcript:

Machine Translation

Can you imagine working as a translator without the help of computer?

Computers help the translator in many ways: Computers help the translator in many ways: CD-rom versions of dictionaries CD-rom versions of dictionaries word processor word processor term banks term banks thesauruses thesauruses the Internet the Internet

Machine Translation (MT): - form of translation where a computer program analyses the text in one language (the ST) and then attempts to produce another, equivalent text in another language (the TT) without human intervention - form of translation where a computer program analyses the text in one language (the ST) and then attempts to produce another, equivalent text in another language (the TT) without human intervention

History of Machine Translation

The goal was the automatic translation of all kinds of documents at a quality equaling that of the best human translators. In fact, it became apparent very soon that this goal was impossible

7 January 1954 the first public demonstration of a Russian-English MT system held in New York at the head office of IBM (system having just 250 words and translating just 49 Russian sentences into English the Cold War system producing rough translation of Russian scientific journals in order to intercept secret information the early 70s the Russian-English project called SYSTRAN - an attempt to translate a vast body of terminology connected with the military by 2010 the IBM company will have released a computer (Super Human Speech Recognition) able to comprehend 20 languages, irrespective of context, tone of voice and the speakers accent

Currently, most machine translation systems produce a "gisting translation" - a rough translation that gives the "gist" of the ST which is then revised (post-edited) by translators

Despite their limitations, MT programs are currently used by various organizations and multilingual bodies around the world, such as the European Union, which has large volumes of technical and administrative documentation that have to be translated into many languages. Despite their limitations, MT programs are currently used by various organizations and multilingual bodies around the world, such as the European Union, which has large volumes of technical and administrative documentation that have to be translated into many languages.

Machine translation (MT) vs Machine-assisted translation (MAT) = Computer-assisted translation (CAT) In MT, the translator supports the machine: the computer program translates the text, which is then edited by the translator In MT, the translator supports the machine: the computer program translates the text, which is then edited by the translator In MAT/CAT, the computer program supports the translator, who translates the text himself, making all the essential decisions involved In MAT/CAT, the computer program supports the translator, who translates the text himself, making all the essential decisions involved

MT concentrates on transferring from one language to another lexical phrases standing in isolation, neglecting the context

Russian MT system translated: The spirit is willing, but the flesh is weak into a Russian equivalent of: The vodka is good, but the steak is lousy

References Austermühl, Frank (2001) Electronic Tools For Translators Austermühl, Frank (2001) Electronic Tools For Translators an introductory guide to MT by D.J.Arnold (1994) an introductory guide to MT by D.J.Arnold (1994) Free-to-use machine translation on the web: Free-to-use machine translation on the web: (Free human translation service) (Free human translation service) (uses Systran software) (uses Systran software) (the Systran site) (the Systran site) (uses Systran software) (uses Systran software) (uses Systran software) (uses Systran software)