SlideShare a Scribd company logo
1 of 23
An Overview
of Machine
Translation




         A
    Presentation
        by:
Outline
2



    ļ± Introduction
    ļ± A brief introduction to Translation technology
    ļ± Interest in MT
    ļ± Problems Involved in Machine Translation
    ļ±Translation Technology
    ļ± Knowledge-based systems
    ļ± Statistical machine translation systems
    ļ± Rule-Based vs. Statistical MT
    ļ± Current State of Machine Translation in Use
    ļ±Personal Speech-to-Speech Translators


                                 Machine Translation
Introduction
3




ā€¢These factors have increased both the
demand for translation services and
interest in computerized translation
technology.




ā€¢Some industry observers say machine
translation, a largely experimental
technology that has been around since
the late 1950s, is now ready to become
commercially viable.
                                   Machine Translation
Definition

                               The sub-domain of artificial
                               intelligence concerned with the
                               task of developing programs
                               possessing some capability of
              NLP                            ā€™ a natural language
                               in order to achieve some specific
                               goal.




A transformation from one
representation (the input text) to               Understanding
another (internal representation)



                               Machine Translation
Introduction:
5



Machine Translation :



The use of computers to
translate from one language
to another.


One of the oldest dreams of
NLP, AI, and CS
(first system in 1954).




                              Machine Translation
6




    Why Machine Translation?

    ā€¢Cheap, universal access to
    worldā€™s online information
    regardless of original language.

    (Thatā€™s the goal)




                               Machine Translation
Interest in MT
7




                                 Interest in MT


    Commercial interest                                             Academic interest


                                 challenging problems in     Requires knowledge from
      U.S. has invested in MT                                                               transferring resources from one
                                      NLP research            many NLP sub-areas
                                                                                                  language to another

      MT is popular on the web                  lexical semantics            parsing


      EU spends more than $1                                                  statistical
                                                morphological analysis
        billion on translation                                                modeling


         (Semi-)automated
            translation


                                                      Machine Translation
Problems Involved in Machine
       Translation
8


            Ambiguity

            syntactic irregularity

            multiple word meanings

            the influence of context
    are the main problems faced by MT systems.

    A classic example is illustrated in the following pair of
    sentences:


    Time flies like an arrow.


    Fruit flies like an apple.
                                              Machine Translation
How can a machine understand these
    differences?
9


     ļ‚¤ Get   the cat with the gloves.




                             Machine Translation
Outline
10



     ļ± Introduction
     ļ± A brief introduction to Translation technology
     ļ± Interest in MT
     ļ± Problems Involved in Machine Translation
     ļ±Translation Technology
     ļ± Knowledge-based systems
     ļ± Statistical machine translation systems
     ļ± Rule-Based vs. Statistical MT
     ļ± Current State of Machine Translation in Use
     ļ±Personal Speech-to-Speech Translators


                                  Machine Translation
TRANSLATION TECHNOLOGY
11



           ā€¢There are two kinds of machine translation:


                                            ā€¢Knowledge-based systems


                                           ā€¢Statistical machine translation
         ā€¢Knowledge-based systems

     Traditional translation technology takes a knowledge-
     based approach.
     These expert systemsā€”used by vendors such as Fujitsu,
     Logos, and Systranā€”translate documents by converting
     words and grammar directly from one language into
     another.

                                           Machine Translation
Knowledge-based systems
12

How they work.
                                                                       Hmm, every time he sees
Knowledge based systems                                                ā€•bancoā€–, he either types
rely on programmers to enter                                           ā€•bankā€– or ā€•benchā€– ā€¦ but if
various languagesā€™ vocabulary      Man, this is so boring.             he sees ā€•banco deā€¦ā€–,
                                                                       he always types ā€•bankā€–,
and syntax information into                                            never ā€•benchā€–ā€¦
data bases.

The programmers then write
lists of rules that describe the
possible relationships
between a languageā€™s parts of
speech.

The software, which can run
                                                             Translated documents
on a high-powered PC,
analyzes a document and
examines the rules for both the             Machine Translation                12
textā€™s language and the target
Statistical machine translation systems
13


                                    Rather than using the knowledge based systemā€™s
       Statistical machine translation
                                    direct word-by-word translation techniques, statistical
                                    approaches translate documents by statistically
                                    analyzing entire phrases and, over time, ā€•learningā€–
                                    how various languages work.

     How it works. Statistical systems
     start with minimal dictionary and language
     resources. Users then must train the
     system before they can work with it on
     extensive translations.
     During the training, researchers feed the
     system documents for which they already
     have accurate human translations.
     The system then uses its resources to
     guess at
      the documentsā€™ meanings.
                                           Machine Translation
Statistical machine translation
14
     systems
 Statistical systems generally work by
 dividing documents into N-grams, with N
 the number of words, usually three, in a
 phrase. N-grams are statistical translationā€™s
 building blocks.




 Analyzing N-grams helps improve
 translation accuracy and performance
 because, while a word by itself may have
 many definitions, it has far fewer potential
 meanings when used as part of a phrase.
                                       Machine Translation
Statistical machine translation
15
       systems


                                        Machine
                                        Learning
                                         Magic


        Books in       Same books,
        English        in Farsi                               P(F|E) model

     Statistical machine translation (SMT) can be defined as the process of
     maximizing the probability of a sentence s in the source language
     matching a sentence t in the target language. We call collections stored
     in two languages parallel corpora or parallel texts.
                                        Machine Translation
Statistical machine translation
16
     systems
 Statistical machine translation systems, which
 statistically analyze entire phrases and ā€•learnā€– how
 various languages work, frequently work with other
 types of systems to improve output quality.

 The lexicon system provides translated words and their
 variations.

 The alignment system assures that phrases from the
 source language are converted to the proper phrases
 and presented in the proper order in the target
 language.

 The language system performs a morphological
 analysis of individual words or a syntactic analysis of
 sentences and thereby produces translations that read
 properly.                                 Machine Translation
Rule-Based vs. Statistical MT
17

 ļ‚Ø   Rule-based MT:
     ļ‚¤   very labour intensive, time-consuming, and expensive
     ļ‚¤   Rules can be based on lexical or structural transfer
     ļ‚¤   Each program must be customized for each language-pair it works with.

     ļ‚¤   Pro: firm grip on complex translation phenomena
     ļ‚¤   Con: time-consuming, and expensive,Often very labor-intensive -> lack
         of robustness

 ļ‚Ø   Statistical MT
     ļ‚¤   Mainly word or phrase-based translations
     ļ‚¤   Translation are learned from actual data
     ļ‚¤   In general, in statistical machine translation, if more data will be
         provided for learning; higher will be the quality of translation.

     ļ‚¤   Pro: Translations are learned automatically
     ļ‚¤   Con: Difficult to model complex translation phenomena
                                           Machine Translation
Current State of Machine Translation in
     Use
18




     Google Translate is a service provided by
     Google Inc. to translate a section of text, or a
     webpage, into another language, with limits to
     the number of paragraphs, or range of
     technical terms, translated. For some
     languages, users are asked for alternative
     translations, such as for technical terms, to be
     included for future updates to the translation
     process. Google translate is based on an
     approach called statistical machine translation.


                                          Machine Translation
Current State of Machine Translation in Use
     cont.
19




            SYSTRAN's methodology is a sentence by sentence approach,
            concentrating on individual words and their dictionary data, then
            on the parse of the sentence unit, followed by the translation of
            the parsed sentence.

           AltaVistaā€™s Babel fish
           Babel Fish is a web-based application developed by AltaVista
           (now part of Yahoo!) which automatically translates text or
           web pages from one of several languages into another. The
           translation technology for Babel Fish is provided by
           SYSTRAN, whose technology also powers a number of other
           sites and portals.


                                    Machine Translation
Current State of Machine Translation in Use
     cont.
20



           is a Los Angeles, Californiaā€“based company that was founded in 2002
           by the University of Southern California's Kevin Knight and Daniel
           Marcu, to commercialize a statistical approach to automatic |language
           translation and natural language processing - now known globally as
           statistical machine translation software (SMTS)
           Language Weaverā€™s statistically-based translation software is an
           instance of a recent advance in automated translation.


             is a service provided by Microsoft as part of its
             Windows Live services which allow users to translate
             texts or entire web pages into different languages.
             Computer-related texts are translated by Microsoft's
             own statistical machine translation technology for eight
             supported languages

                                   Machine Translation
Personal Speech-to-Speech
Translators
21


ā€¢One of the newest research areas in machine translation is the personal speech to-
speech translator. People on business or personal trips could use these devices to
translate on the fly.
Speech-to-speech translation, which is still in the experimental
stage, is a complex process requiring speech-recognition
technology that converts speech to text, machine translation of the text, and then text-
to-speech conversion.
ā€¢IBM is working on the handheld multilingual automatic speech-to-speech translator
(Mastor), which uses a hybrid statistical/knowledge-base engine to translate the
content. Mastor tries to determine the general meaning of a phrase, rather than its
exact translation. This approach requires less database capacity, which makes it more
suitable for small devices.




                                         Machine Translation
LOOKING AHEAD
22




     ā€¢Because of ongoing
     demand for better
     translation systems,
     research money will
     continue to flow into the
     field. In addition,
     companies are likely to
     develop and release more
     commercial products.
                            Machine Translation
Questions ?
23

      http://www.youtube.com/watch?v=jZCecsdlM7Q




                                  Machine Translation

More Related Content

What's hot

Introduction to natural language processing
Introduction to natural language processingIntroduction to natural language processing
Introduction to natural language processingMinh Pham
Ā 
A tutorial on Machine Translation
A tutorial on Machine TranslationA tutorial on Machine Translation
A tutorial on Machine TranslationJaganadh Gopinadhan
Ā 
natural language processing help at myassignmenthelp.net
natural language processing  help at myassignmenthelp.netnatural language processing  help at myassignmenthelp.net
natural language processing help at myassignmenthelp.netwww.myassignmenthelp.net
Ā 
Natural language processing (NLP)
Natural language processing (NLP) Natural language processing (NLP)
Natural language processing (NLP) ASWINKP11
Ā 
Natural language processing (nlp)
Natural language processing (nlp)Natural language processing (nlp)
Natural language processing (nlp)Kuppusamy P
Ā 
Text summarization
Text summarizationText summarization
Text summarizationkareemhashem
Ā 
Types of machine translation
Types of machine translationTypes of machine translation
Types of machine translationRushdi Shams
Ā 
Introduction to Natural Language Processing (NLP)
Introduction to Natural Language Processing (NLP)Introduction to Natural Language Processing (NLP)
Introduction to Natural Language Processing (NLP)VenkateshMurugadas
Ā 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language ProcessingYasir Khan
Ā 
Syntactic analysis in NLP
Syntactic analysis in NLPSyntactic analysis in NLP
Syntactic analysis in NLPkartikaVashisht
Ā 
Natural lanaguage processing
Natural lanaguage processingNatural lanaguage processing
Natural lanaguage processinggulshan kumar
Ā 
Stemming And Lemmatization Tutorial | Natural Language Processing (NLP) With ...
Stemming And Lemmatization Tutorial | Natural Language Processing (NLP) With ...Stemming And Lemmatization Tutorial | Natural Language Processing (NLP) With ...
Stemming And Lemmatization Tutorial | Natural Language Processing (NLP) With ...Edureka!
Ā 
Introduction to Natural Language Processing
Introduction to Natural Language ProcessingIntroduction to Natural Language Processing
Introduction to Natural Language ProcessingPranav Gupta
Ā 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language ProcessingJaganadh Gopinadhan
Ā 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language ProcessingRishikese MR
Ā 
Parts of Speect Tagging
Parts of Speect TaggingParts of Speect Tagging
Parts of Speect Taggingtheyaseen51
Ā 
What is machine translation
What is machine translationWhat is machine translation
What is machine translationStephen Peacock
Ā 
Natural language processing
Natural language processing Natural language processing
Natural language processing Md.Sumon Sarder
Ā 

What's hot (20)

Introduction to natural language processing
Introduction to natural language processingIntroduction to natural language processing
Introduction to natural language processing
Ā 
A tutorial on Machine Translation
A tutorial on Machine TranslationA tutorial on Machine Translation
A tutorial on Machine Translation
Ā 
natural language processing help at myassignmenthelp.net
natural language processing  help at myassignmenthelp.netnatural language processing  help at myassignmenthelp.net
natural language processing help at myassignmenthelp.net
Ā 
Natural language processing (NLP)
Natural language processing (NLP) Natural language processing (NLP)
Natural language processing (NLP)
Ā 
Natural language processing (nlp)
Natural language processing (nlp)Natural language processing (nlp)
Natural language processing (nlp)
Ā 
Text summarization
Text summarizationText summarization
Text summarization
Ā 
Machine translator Introduction
Machine translator IntroductionMachine translator Introduction
Machine translator Introduction
Ā 
Types of machine translation
Types of machine translationTypes of machine translation
Types of machine translation
Ā 
Introduction to Natural Language Processing (NLP)
Introduction to Natural Language Processing (NLP)Introduction to Natural Language Processing (NLP)
Introduction to Natural Language Processing (NLP)
Ā 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
Ā 
Syntactic analysis in NLP
Syntactic analysis in NLPSyntactic analysis in NLP
Syntactic analysis in NLP
Ā 
Natural lanaguage processing
Natural lanaguage processingNatural lanaguage processing
Natural lanaguage processing
Ā 
Stemming And Lemmatization Tutorial | Natural Language Processing (NLP) With ...
Stemming And Lemmatization Tutorial | Natural Language Processing (NLP) With ...Stemming And Lemmatization Tutorial | Natural Language Processing (NLP) With ...
Stemming And Lemmatization Tutorial | Natural Language Processing (NLP) With ...
Ā 
Introduction to Natural Language Processing
Introduction to Natural Language ProcessingIntroduction to Natural Language Processing
Introduction to Natural Language Processing
Ā 
Nlp ambiguity presentation
Nlp ambiguity presentationNlp ambiguity presentation
Nlp ambiguity presentation
Ā 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
Ā 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
Ā 
Parts of Speect Tagging
Parts of Speect TaggingParts of Speect Tagging
Parts of Speect Tagging
Ā 
What is machine translation
What is machine translationWhat is machine translation
What is machine translation
Ā 
Natural language processing
Natural language processing Natural language processing
Natural language processing
Ā 

Similar to Machine Tanslation

Integration of speech recognition with computer assisted translation
Integration of speech recognition with computer assisted translationIntegration of speech recognition with computer assisted translation
Integration of speech recognition with computer assisted translationChamani Shiranthika
Ā 
Jawaharlal Nehru Technological University Natural Language Processing Capston...
Jawaharlal Nehru Technological University Natural Language Processing Capston...Jawaharlal Nehru Technological University Natural Language Processing Capston...
Jawaharlal Nehru Technological University Natural Language Processing Capston...write4
Ā 
Jawaharlal Nehru Technological University Natural Language Processing Capston...
Jawaharlal Nehru Technological University Natural Language Processing Capston...Jawaharlal Nehru Technological University Natural Language Processing Capston...
Jawaharlal Nehru Technological University Natural Language Processing Capston...write5
Ā 
CH 01.pptx
CH 01.pptxCH 01.pptx
CH 01.pptxObsa2
Ā 
Translationusing moses1
Translationusing moses1Translationusing moses1
Translationusing moses1Kalyanee Baruah
Ā 
Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)
Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)
Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)TAUS - The Language Data Network
Ā 
Machine translation with statistical approach
Machine translation with statistical approachMachine translation with statistical approach
Machine translation with statistical approachvini89
Ā 
APznzaalselifJKjGQdTCA51cF7bldYdFMvDcshM8opKFZ_ZaIV-dqkiLoIKIfhz2tS6Fw5UBk25u...
APznzaalselifJKjGQdTCA51cF7bldYdFMvDcshM8opKFZ_ZaIV-dqkiLoIKIfhz2tS6Fw5UBk25u...APznzaalselifJKjGQdTCA51cF7bldYdFMvDcshM8opKFZ_ZaIV-dqkiLoIKIfhz2tS6Fw5UBk25u...
APznzaalselifJKjGQdTCA51cF7bldYdFMvDcshM8opKFZ_ZaIV-dqkiLoIKIfhz2tS6Fw5UBk25u...AishwaryaChemate
Ā 
Machine Translation
Machine TranslationMachine Translation
Machine TranslationUwe Muegge
Ā 
Machine Translation Approaches and Design Aspects
Machine Translation Approaches and Design AspectsMachine Translation Approaches and Design Aspects
Machine Translation Approaches and Design AspectsIOSR Journals
Ā 
NLP unit-VI.pptx
NLP unit-VI.pptxNLP unit-VI.pptx
NLP unit-VI.pptxaishuchemate01
Ā 
The Latest Advances in Patent Machine Translation
The Latest Advances in Patent Machine TranslationThe Latest Advances in Patent Machine Translation
The Latest Advances in Patent Machine TranslationIconic Translation Machines
Ā 
Introduction to Natural Language Processing
Introduction to Natural Language ProcessingIntroduction to Natural Language Processing
Introduction to Natural Language ProcessingMercy Rani
Ā 
machine transaltion
machine transaltionmachine transaltion
machine transaltionAbhishek Gupta
Ā 
Past, Present, and Future: Machine Translation & Natural Language Processing ...
Past, Present, and Future: Machine Translation & Natural Language Processing ...Past, Present, and Future: Machine Translation & Natural Language Processing ...
Past, Present, and Future: Machine Translation & Natural Language Processing ...John Tinsley
Ā 
Past, Present, and Future: Machine Translation & Natural Language Processing ...
Past, Present, and Future: Machine Translation & Natural Language Processing ...Past, Present, and Future: Machine Translation & Natural Language Processing ...
Past, Present, and Future: Machine Translation & Natural Language Processing ...Iconic Translation Machines
Ā 
Lecture_1_Introduction_to_Programming.pptx
Lecture_1_Introduction_to_Programming.pptxLecture_1_Introduction_to_Programming.pptx
Lecture_1_Introduction_to_Programming.pptxChewe Lulembo
Ā 

Similar to Machine Tanslation (20)

Integration of speech recognition with computer assisted translation
Integration of speech recognition with computer assisted translationIntegration of speech recognition with computer assisted translation
Integration of speech recognition with computer assisted translation
Ā 
E-Translation
E-TranslationE-Translation
E-Translation
Ā 
Jawaharlal Nehru Technological University Natural Language Processing Capston...
Jawaharlal Nehru Technological University Natural Language Processing Capston...Jawaharlal Nehru Technological University Natural Language Processing Capston...
Jawaharlal Nehru Technological University Natural Language Processing Capston...
Ā 
Jawaharlal Nehru Technological University Natural Language Processing Capston...
Jawaharlal Nehru Technological University Natural Language Processing Capston...Jawaharlal Nehru Technological University Natural Language Processing Capston...
Jawaharlal Nehru Technological University Natural Language Processing Capston...
Ā 
CH 01.pptx
CH 01.pptxCH 01.pptx
CH 01.pptx
Ā 
Translationusing moses1
Translationusing moses1Translationusing moses1
Translationusing moses1
Ā 
Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)
Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)
Topic 4: The Magician's Hat: Turning Data into Business Intelligence (3)
Ā 
Machine translation with statistical approach
Machine translation with statistical approachMachine translation with statistical approach
Machine translation with statistical approach
Ā 
APznzaalselifJKjGQdTCA51cF7bldYdFMvDcshM8opKFZ_ZaIV-dqkiLoIKIfhz2tS6Fw5UBk25u...
APznzaalselifJKjGQdTCA51cF7bldYdFMvDcshM8opKFZ_ZaIV-dqkiLoIKIfhz2tS6Fw5UBk25u...APznzaalselifJKjGQdTCA51cF7bldYdFMvDcshM8opKFZ_ZaIV-dqkiLoIKIfhz2tS6Fw5UBk25u...
APznzaalselifJKjGQdTCA51cF7bldYdFMvDcshM8opKFZ_ZaIV-dqkiLoIKIfhz2tS6Fw5UBk25u...
Ā 
Machine Translation
Machine TranslationMachine Translation
Machine Translation
Ā 
Machine Translation Approaches and Design Aspects
Machine Translation Approaches and Design AspectsMachine Translation Approaches and Design Aspects
Machine Translation Approaches and Design Aspects
Ā 
Introduction to programming languages part 1
Introduction to programming languages   part 1Introduction to programming languages   part 1
Introduction to programming languages part 1
Ā 
sample PPT.pptx
sample PPT.pptxsample PPT.pptx
sample PPT.pptx
Ā 
NLP unit-VI.pptx
NLP unit-VI.pptxNLP unit-VI.pptx
NLP unit-VI.pptx
Ā 
The Latest Advances in Patent Machine Translation
The Latest Advances in Patent Machine TranslationThe Latest Advances in Patent Machine Translation
The Latest Advances in Patent Machine Translation
Ā 
Introduction to Natural Language Processing
Introduction to Natural Language ProcessingIntroduction to Natural Language Processing
Introduction to Natural Language Processing
Ā 
machine transaltion
machine transaltionmachine transaltion
machine transaltion
Ā 
Past, Present, and Future: Machine Translation & Natural Language Processing ...
Past, Present, and Future: Machine Translation & Natural Language Processing ...Past, Present, and Future: Machine Translation & Natural Language Processing ...
Past, Present, and Future: Machine Translation & Natural Language Processing ...
Ā 
Past, Present, and Future: Machine Translation & Natural Language Processing ...
Past, Present, and Future: Machine Translation & Natural Language Processing ...Past, Present, and Future: Machine Translation & Natural Language Processing ...
Past, Present, and Future: Machine Translation & Natural Language Processing ...
Ā 
Lecture_1_Introduction_to_Programming.pptx
Lecture_1_Introduction_to_Programming.pptxLecture_1_Introduction_to_Programming.pptx
Lecture_1_Introduction_to_Programming.pptx
Ā 

Recently uploaded

Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
Ā 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
Ā 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
Ā 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
Ā 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
Ā 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
Ā 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
Ā 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
Ā 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
Ā 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
Ā 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
Ā 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
Ā 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
Ā 
šŸ¬ The future of MySQL is Postgres šŸ˜
šŸ¬  The future of MySQL is Postgres   šŸ˜šŸ¬  The future of MySQL is Postgres   šŸ˜
šŸ¬ The future of MySQL is Postgres šŸ˜RTylerCroy
Ā 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
Ā 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
Ā 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
Ā 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel AraĆŗjo
Ā 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
Ā 
Scaling API-first ā€“ The story of a global engineering organization
Scaling API-first ā€“ The story of a global engineering organizationScaling API-first ā€“ The story of a global engineering organization
Scaling API-first ā€“ The story of a global engineering organizationRadu Cotescu
Ā 

Recently uploaded (20)

Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
Ā 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Ā 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
Ā 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
Ā 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
Ā 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
Ā 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
Ā 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
Ā 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Ā 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
Ā 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
Ā 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
Ā 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
Ā 
šŸ¬ The future of MySQL is Postgres šŸ˜
šŸ¬  The future of MySQL is Postgres   šŸ˜šŸ¬  The future of MySQL is Postgres   šŸ˜
šŸ¬ The future of MySQL is Postgres šŸ˜
Ā 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
Ā 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
Ā 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
Ā 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Ā 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
Ā 
Scaling API-first ā€“ The story of a global engineering organization
Scaling API-first ā€“ The story of a global engineering organizationScaling API-first ā€“ The story of a global engineering organization
Scaling API-first ā€“ The story of a global engineering organization
Ā 

Machine Tanslation

  • 2. Outline 2 ļ± Introduction ļ± A brief introduction to Translation technology ļ± Interest in MT ļ± Problems Involved in Machine Translation ļ±Translation Technology ļ± Knowledge-based systems ļ± Statistical machine translation systems ļ± Rule-Based vs. Statistical MT ļ± Current State of Machine Translation in Use ļ±Personal Speech-to-Speech Translators Machine Translation
  • 3. Introduction 3 ā€¢These factors have increased both the demand for translation services and interest in computerized translation technology. ā€¢Some industry observers say machine translation, a largely experimental technology that has been around since the late 1950s, is now ready to become commercially viable. Machine Translation
  • 4. Definition The sub-domain of artificial intelligence concerned with the task of developing programs possessing some capability of NLP ā€™ a natural language in order to achieve some specific goal. A transformation from one representation (the input text) to Understanding another (internal representation) Machine Translation
  • 5. Introduction: 5 Machine Translation : The use of computers to translate from one language to another. One of the oldest dreams of NLP, AI, and CS (first system in 1954). Machine Translation
  • 6. 6 Why Machine Translation? ā€¢Cheap, universal access to worldā€™s online information regardless of original language. (Thatā€™s the goal) Machine Translation
  • 7. Interest in MT 7 Interest in MT Commercial interest Academic interest challenging problems in Requires knowledge from U.S. has invested in MT transferring resources from one NLP research many NLP sub-areas language to another MT is popular on the web lexical semantics parsing EU spends more than $1 statistical morphological analysis billion on translation modeling (Semi-)automated translation Machine Translation
  • 8. Problems Involved in Machine Translation 8 Ambiguity syntactic irregularity multiple word meanings the influence of context are the main problems faced by MT systems. A classic example is illustrated in the following pair of sentences: Time flies like an arrow. Fruit flies like an apple. Machine Translation
  • 9. How can a machine understand these differences? 9 ļ‚¤ Get the cat with the gloves. Machine Translation
  • 10. Outline 10 ļ± Introduction ļ± A brief introduction to Translation technology ļ± Interest in MT ļ± Problems Involved in Machine Translation ļ±Translation Technology ļ± Knowledge-based systems ļ± Statistical machine translation systems ļ± Rule-Based vs. Statistical MT ļ± Current State of Machine Translation in Use ļ±Personal Speech-to-Speech Translators Machine Translation
  • 11. TRANSLATION TECHNOLOGY 11 ā€¢There are two kinds of machine translation: ā€¢Knowledge-based systems ā€¢Statistical machine translation ā€¢Knowledge-based systems Traditional translation technology takes a knowledge- based approach. These expert systemsā€”used by vendors such as Fujitsu, Logos, and Systranā€”translate documents by converting words and grammar directly from one language into another. Machine Translation
  • 12. Knowledge-based systems 12 How they work. Hmm, every time he sees Knowledge based systems ā€•bancoā€–, he either types rely on programmers to enter ā€•bankā€– or ā€•benchā€– ā€¦ but if various languagesā€™ vocabulary Man, this is so boring. he sees ā€•banco deā€¦ā€–, he always types ā€•bankā€–, and syntax information into never ā€•benchā€–ā€¦ data bases. The programmers then write lists of rules that describe the possible relationships between a languageā€™s parts of speech. The software, which can run Translated documents on a high-powered PC, analyzes a document and examines the rules for both the Machine Translation 12 textā€™s language and the target
  • 13. Statistical machine translation systems 13 Rather than using the knowledge based systemā€™s Statistical machine translation direct word-by-word translation techniques, statistical approaches translate documents by statistically analyzing entire phrases and, over time, ā€•learningā€– how various languages work. How it works. Statistical systems start with minimal dictionary and language resources. Users then must train the system before they can work with it on extensive translations. During the training, researchers feed the system documents for which they already have accurate human translations. The system then uses its resources to guess at the documentsā€™ meanings. Machine Translation
  • 14. Statistical machine translation 14 systems Statistical systems generally work by dividing documents into N-grams, with N the number of words, usually three, in a phrase. N-grams are statistical translationā€™s building blocks. Analyzing N-grams helps improve translation accuracy and performance because, while a word by itself may have many definitions, it has far fewer potential meanings when used as part of a phrase. Machine Translation
  • 15. Statistical machine translation 15 systems Machine Learning Magic Books in Same books, English in Farsi P(F|E) model Statistical machine translation (SMT) can be defined as the process of maximizing the probability of a sentence s in the source language matching a sentence t in the target language. We call collections stored in two languages parallel corpora or parallel texts. Machine Translation
  • 16. Statistical machine translation 16 systems Statistical machine translation systems, which statistically analyze entire phrases and ā€•learnā€– how various languages work, frequently work with other types of systems to improve output quality. The lexicon system provides translated words and their variations. The alignment system assures that phrases from the source language are converted to the proper phrases and presented in the proper order in the target language. The language system performs a morphological analysis of individual words or a syntactic analysis of sentences and thereby produces translations that read properly. Machine Translation
  • 17. Rule-Based vs. Statistical MT 17 ļ‚Ø Rule-based MT: ļ‚¤ very labour intensive, time-consuming, and expensive ļ‚¤ Rules can be based on lexical or structural transfer ļ‚¤ Each program must be customized for each language-pair it works with. ļ‚¤ Pro: firm grip on complex translation phenomena ļ‚¤ Con: time-consuming, and expensive,Often very labor-intensive -> lack of robustness ļ‚Ø Statistical MT ļ‚¤ Mainly word or phrase-based translations ļ‚¤ Translation are learned from actual data ļ‚¤ In general, in statistical machine translation, if more data will be provided for learning; higher will be the quality of translation. ļ‚¤ Pro: Translations are learned automatically ļ‚¤ Con: Difficult to model complex translation phenomena Machine Translation
  • 18. Current State of Machine Translation in Use 18 Google Translate is a service provided by Google Inc. to translate a section of text, or a webpage, into another language, with limits to the number of paragraphs, or range of technical terms, translated. For some languages, users are asked for alternative translations, such as for technical terms, to be included for future updates to the translation process. Google translate is based on an approach called statistical machine translation. Machine Translation
  • 19. Current State of Machine Translation in Use cont. 19 SYSTRAN's methodology is a sentence by sentence approach, concentrating on individual words and their dictionary data, then on the parse of the sentence unit, followed by the translation of the parsed sentence. AltaVistaā€™s Babel fish Babel Fish is a web-based application developed by AltaVista (now part of Yahoo!) which automatically translates text or web pages from one of several languages into another. The translation technology for Babel Fish is provided by SYSTRAN, whose technology also powers a number of other sites and portals. Machine Translation
  • 20. Current State of Machine Translation in Use cont. 20 is a Los Angeles, Californiaā€“based company that was founded in 2002 by the University of Southern California's Kevin Knight and Daniel Marcu, to commercialize a statistical approach to automatic |language translation and natural language processing - now known globally as statistical machine translation software (SMTS) Language Weaverā€™s statistically-based translation software is an instance of a recent advance in automated translation. is a service provided by Microsoft as part of its Windows Live services which allow users to translate texts or entire web pages into different languages. Computer-related texts are translated by Microsoft's own statistical machine translation technology for eight supported languages Machine Translation
  • 21. Personal Speech-to-Speech Translators 21 ā€¢One of the newest research areas in machine translation is the personal speech to- speech translator. People on business or personal trips could use these devices to translate on the fly. Speech-to-speech translation, which is still in the experimental stage, is a complex process requiring speech-recognition technology that converts speech to text, machine translation of the text, and then text- to-speech conversion. ā€¢IBM is working on the handheld multilingual automatic speech-to-speech translator (Mastor), which uses a hybrid statistical/knowledge-base engine to translate the content. Mastor tries to determine the general meaning of a phrase, rather than its exact translation. This approach requires less database capacity, which makes it more suitable for small devices. Machine Translation
  • 22. LOOKING AHEAD 22 ā€¢Because of ongoing demand for better translation systems, research money will continue to flow into the field. In addition, companies are likely to develop and release more commercial products. Machine Translation
  • 23. Questions ? 23 http://www.youtube.com/watch?v=jZCecsdlM7Q Machine Translation

Editor's Notes

  1. Ā Statistical machine translation (SMT) can be defined as the process of maximizing the probability of a sentence s in the source language matching a sentence t in the target language.
  2. the knowledge-based approachā€™s is very labour intensive, time-consuming, and expensive. And even after decades of work, the systems donā€™t generally provide more than the basic idea of a documentā€™s meaning. However, until recently, knowledge based systems were still preferred by many researchers who contended that the statistical approach was too simple to effectively handle a complex task like translation. In addition, statistical systems require fast processors and large amounts of RAM, which were not readily and inexpensively available until several years ago.
  3. It is critical to continue research and development in any field, knowing the current state of the technology, rather than re-inventing the wheel. Existing translation engines will be explained in the following slides.
  4. Even as technology opens up e-commerce opportunities, companies must overcome language barriers to reach new potential customers and business partners. For example, many companies have decided to develop Web sites in the languages of the countries in which their customers and partners live.
  5. Building machines to automate tasks requiring intelligent behaviour. Machine Translation (MT) is a subfield of natural language processing that involves automatic translation of sentences from one natural language to another.The sub-domain of artificial intelligence concerned with the task of developing programs possessing some capability of ā€˜understandingā€™ a natural language in order to achieve some specific goal.
  6. Machine Translation also known as Automatic Translation is the process that translates one human language to another. A Machine Translation Systems can be thought of as a compiler. A compiler translates a high-level programming language like C++, Java and the like to low-level languages like assembly and machine language. The only difference being that the grammar of a natural language like English or Hindi is much more complex compared to the grammar of a programming language.
  7. A Machine Translation Systems can be thought of as a compiler. A compiler translates a high-level programming language like C++, Java and the like to low-level languages like assembly and machine language. The only difference being that the grammar of a natural language like English or Hindi is much more complex compared to the grammar of a programming language.
  8. Commercial interest:U.S. has invested in MT for intelligence purposesMT is popular on the webā€”it is the most used of Googleā€™s special featuresEU spends more than $1 billion on translation costs each year.(Semi-)automated translation could lead to huge savingsAcademic interest:One of the most challenging problems in NLP researchRequires knowledge from many NLP sub-areas, e.g., lexical semantics, parsing, morphological analysis, statistical modeling,ā€¦Being able to establish links between two languages allows for transferring resources from one language to another
  9. The sentence construction is parallel, but the meanings are entirely different: the first is a figure of speech involving a metaphor and the second is a literal description. And the identical words in the sentences - flies and like - are used in different grammatical categories