SlideShare uma empresa Scribd logo
1 de 27
Baixar para ler offline
1
Integration of Speech
Recognition with Computer
Assisted Translation
CHAMANI SHIRANTHIKA
UNIVERSITY OF MORATUWA
SRI LANKA
 Introduction
 What is Machine Translation (MT)
 What is Computer Assisted Translation (CAT)
 Technology adapted by CAT and MT
 Technology adapted by Automatic Speech Recognition (ASR)
 ASR and CAT integration
 Translation Quality Evaluation
 New Trends in Machine Translation
 Conclusion
Overview
2
Introduction
 Researches have been undertaken to implement translation tools with out a
use of human translator to increase translation quality and to reduce
human post editing needed
 Speech is the most natural , practical , simplest and efficient method of
human communication
 Integration of Speech to translation process is a wide research area
 As a solution for blind people for the communication with different
languages
3
 Sub categories of Computational Linguistics
 Computational linguistics is the branch of linguistics in which the techniques of computer
science are applied to the analysis and synthesis of language and speech
 Machine Translation is accomplished by feeding a text to a computer algorithm that
automatically translates in to another language. That is there is no human
involvement
 Computer Assisted Translation is human translation carried out with the aid of
computerized tools
What is MT & CAT
4
Technology adapted by MT & CAT
5
 A rule based machine translation system consists of collection of rules called
grammar rules, lexicon and software programs to process the rules
 Focus on syntactic, semantic and morphological details of both the source language
and the translated language when translating
• Syntactic – how words are grammatically arranged in sentences, how we speech in
communication
• Semantic – how words are meaningfully arranged in sentences
• Morphological – structure of sentences, source and targeted language
Rule Based Machine Translation
6
Rule Based Machine Translation (continued..)
Structure of the Rule Based Machine Translation system
• A tree structure is used to represent the structure of the sentence
• A typical English sentence consists of two major parts as the noun phrase (NP) &
the verb phrase (VP)
• These two can be further divided
• Following are the rules to represent a simple grammar
S -> NPVP
VP -> VNP
NP -> Name
NP -> ART N
S stands for sentence, V for verb, N for noun and ART for article
• Example : Saman was happy can be written in logical form as
(< PAST HAPPY> (NAME “Saman”))
7
 Translation based on previous example translations as results of experiments
 Uses knowledge sources to support the translation process
 Require bilingual content
 Two types
• Statistical Machine Translation
• Example Based Machine Translation
Empirical Based Machine Translation
8
Statistical Machine Translation
 Translations based on statistical models
 Statistical Translation Model – Learned from Bilingual Data (TM)
• Probabilistic mapping of equivalencies in source words and phrases with target languag
e words and phrases through the Unsupervised Expected Model (EM) training and word
and phrase alignment process
• Generates a lots of possible translations
• Includes finite state models such as finite state transducers , alignment models and
phrase based models
 Statistical Language Model – Learned from Monolingual Target Language Data
• Probabilistic model of relative fluency and general usage patterns in the target language
• Based on n-gram model
• Target language model selects the “best” translations from a list of possible candidates
• Candidates stored in a N-best list
• Concept of re-ranking
9
• N-gram is a contiguous sequence of n items from a given sequence of text or speech
• When the items are words, n-grams are also called as shingles
• An n-gram of size 1 is a “unigram” , size 2 is a “bigram” , size 3 is “trigram” and so on..
 Advantages : More efficient use of human and data resources
Disadvantages in rule based approach are eliminated
 Disadvantages : Corpus creation can be costly
Errors are hard to predict and fix
Examples : SYSTRAN, ART, METEO, LOGOS, Anusaarka, TC- Star, Google translate
Statistical Machine Translation (continued..)
10
What is Speech Recognition ?
 Speech Recognition is the translation of spoken words into text
 Also called “Automatic Speech Recognition” (ASR), “Computer Speech
Recognition” or just “Speech To Text” (STT)
11
Signal Processing System
12
Machine Learning paradigms for speech recognition
• Hidden Markov Model
• Discriminative Learning
• Structured Sequence Learning
• Bayesian Learning
• Adaptive Learning
• Multi – task Learning
• Active Learning
13
Speech recognition systems
• Google Speech API
• Cloud Speech API
• Microsoft cognitive services – Bing speech API
• API.AI
• Speechmatics
• Vocapia Speech to Text API
• Klaldi
• iSpeech
• Baidu
• Siri
• Hound
• Google Now
14
Integration of ASR & MT
4 approaches
 Word graphs product – Separate large word graphs for ASR and MT system
will be generated and take the product of these using composition operation in
automata theory
 ASR constrained search – Replaced n-gram language model of phrase base
MT with the ASR word graph
 Adapted Language Model – MT system has been improved by adopting it’s
language model to the ASR output
 MT-Derived Language Model – Rescoring the ASR word graph with a
language model that is derived from the MT system
Examples : TELNET, IBM 1,2 Models , SEECAT
15
Combined ASR / SMT Model
P(e) Language Model
P(f|e) Translation Model P(x|e) Acoustic Model
e = argmax {P(e). P(f|e).P(x|e)}
e: Target Language
Text
x: Speechf: Source Language
16
Loose Integration & Tight Integration approaches
Loose Integration approach
• P(e) has 2 components
• PS(e) – characterizes those aspects of language that can be acquired from large t
ext corpora in the target language
• PM(e) – represents the effects that can be acquired from the source language text
P(e) = (λM) PM(e) + (λS) PS(e)
Assumption :- These 2 models are independent
P(e) = (λM) PM(e) . (λS) PS(e)
P(e) = PM(e) λM. PS(e) λS
17
Tight Integration approach
• Involves using SMT to reevaluate ASR hypothesis
• Each string hypothesis appearing in the ASR N-best list is rescored using the language translation
probability, P(f|e) obtained from the SMT
• The score for each string is combined from a log linear combination of acoustic, language model &
translation model probabilities
e = argmaxe { (λ1) log(P(e)) + (λ2) log(P(f|e)) + (λ3) log(P(x|e)) }
18
Translation Quality Evaluation
 TWER or edit distance
 CSR
 BLEU
 KSR
 MAR
 SER
 F – Measure
 TER Scores
19
New trends in Machine Translation
• Neural MT
• Google Translate -> Phrase based which breaks an input sentence into words and phrases to be
translated largely independently
• GNMT -> considers the entire input sentence as a unit for translation
• Map the meaning of a sentence into a fixed-length vector representation and then generate a
translation based on that vector
• Advantages over Google Translate ---
 it requires fewer engineering design choices
 Easier to build and train
 Small memory footprint
 Generalize well to long sequences
20
GNMT translating a Chinese sentence to English
21
Neural MT of Microsoft
22
Encode
Encode
Encode
Final Output Matrix
Attention Layer
500 dimension vector
1000 dimension vector
ASR – MT System of Microsoft
23
Automatic Speech
Recognition
True Text Machine
Translation
Text To Speech
MT in 2017 (Some popular and publicly available commercial systems)
• Microsoft
• Microsoft Adapted
• Systran Neural
• SDL
• SDL Adapted
• Lilt
• Lilt Adapted
• Lilt Interactive
• A/B Testing
• Convergence of TM and MT Systems
• Adoption of MT for instant web publishing
• NMT + SMT/RBMT approach
• NMT for mobile devices
24
Deep learning in to MT
Attention Mechanism
• NMT translates the whole sentence at once
• Able to translate very long sentences
• Attention retains a memory of source hidden states (Random Access Memory)
• Compare target and source hidden states
• Learning both translation & alignment
• Local attention & Global attention 25
Conclusion
 Implemented models are still in developing era
 Statistical approaches and language models have been popularized so far
 Speech recognition tools have been developed so far
 Concept of AI , ML can be integrated
Future works
 Approaches to minimize the human post editing in translation
 Increase the quality of available translation tools
 Enhance the effectiveness of speech recognition paradigm
 A method of communication with other languages, for blind people so that they can enter a
speech input and can get responses in their language by means of speech to text conversion 26
27

Mais conteúdo relacionado

Mais procurados

7. Trevor Cohn (usfd) Statistical Machine Translation
7. Trevor Cohn (usfd) Statistical Machine Translation7. Trevor Cohn (usfd) Statistical Machine Translation
7. Trevor Cohn (usfd) Statistical Machine Translation
RIILP
 
CUHK intern PPT. Machine Translation Evaluation: Methods and Tools
CUHK intern PPT. Machine Translation Evaluation: Methods and Tools CUHK intern PPT. Machine Translation Evaluation: Methods and Tools
CUHK intern PPT. Machine Translation Evaluation: Methods and Tools
Lifeng (Aaron) Han
 
13. Constantin Orasan (UoW) Natural Language Processing for Translation
13. Constantin Orasan (UoW) Natural Language Processing for Translation13. Constantin Orasan (UoW) Natural Language Processing for Translation
13. Constantin Orasan (UoW) Natural Language Processing for Translation
RIILP
 
5. manuel arcedillo & juanjo arevalillo (hermes) translation memories
5. manuel arcedillo & juanjo arevalillo (hermes) translation memories5. manuel arcedillo & juanjo arevalillo (hermes) translation memories
5. manuel arcedillo & juanjo arevalillo (hermes) translation memories
RIILP
 
Machine translation with statistical approach
Machine translation with statistical approachMachine translation with statistical approach
Machine translation with statistical approach
vini89
 

Mais procurados (20)

7. Trevor Cohn (usfd) Statistical Machine Translation
7. Trevor Cohn (usfd) Statistical Machine Translation7. Trevor Cohn (usfd) Statistical Machine Translation
7. Trevor Cohn (usfd) Statistical Machine Translation
 
CUHK intern PPT. Machine Translation Evaluation: Methods and Tools
CUHK intern PPT. Machine Translation Evaluation: Methods and Tools CUHK intern PPT. Machine Translation Evaluation: Methods and Tools
CUHK intern PPT. Machine Translation Evaluation: Methods and Tools
 
Natural Language Processing Advancements By Deep Learning - A Survey
Natural Language Processing Advancements By Deep Learning - A SurveyNatural Language Processing Advancements By Deep Learning - A Survey
Natural Language Processing Advancements By Deep Learning - A Survey
 
EMPLOYING PIVOT LANGUAGE TECHNIQUE THROUGH STATISTICAL AND NEURAL MACHINE TRA...
EMPLOYING PIVOT LANGUAGE TECHNIQUE THROUGH STATISTICAL AND NEURAL MACHINE TRA...EMPLOYING PIVOT LANGUAGE TECHNIQUE THROUGH STATISTICAL AND NEURAL MACHINE TRA...
EMPLOYING PIVOT LANGUAGE TECHNIQUE THROUGH STATISTICAL AND NEURAL MACHINE TRA...
 
[PACLING2019] Improving Context-aware Neural Machine Translation with Target-...
[PACLING2019] Improving Context-aware Neural Machine Translation with Target-...[PACLING2019] Improving Context-aware Neural Machine Translation with Target-...
[PACLING2019] Improving Context-aware Neural Machine Translation with Target-...
 
2010 PACLIC - pay attention to categories
2010 PACLIC - pay attention to categories2010 PACLIC - pay attention to categories
2010 PACLIC - pay attention to categories
 
13. Constantin Orasan (UoW) Natural Language Processing for Translation
13. Constantin Orasan (UoW) Natural Language Processing for Translation13. Constantin Orasan (UoW) Natural Language Processing for Translation
13. Constantin Orasan (UoW) Natural Language Processing for Translation
 
Bert
BertBert
Bert
 
Natural Language Processing Advancements By Deep Learning: A Survey
Natural Language Processing Advancements By Deep Learning: A SurveyNatural Language Processing Advancements By Deep Learning: A Survey
Natural Language Processing Advancements By Deep Learning: A Survey
 
5. manuel arcedillo & juanjo arevalillo (hermes) translation memories
5. manuel arcedillo & juanjo arevalillo (hermes) translation memories5. manuel arcedillo & juanjo arevalillo (hermes) translation memories
5. manuel arcedillo & juanjo arevalillo (hermes) translation memories
 
1909 paclic
1909 paclic1909 paclic
1909 paclic
 
Tamil-English Document Translation Using Statistical Machine Translation Appr...
Tamil-English Document Translation Using Statistical Machine Translation Appr...Tamil-English Document Translation Using Statistical Machine Translation Appr...
Tamil-English Document Translation Using Statistical Machine Translation Appr...
 
Deep Learning for Machine Translation
Deep Learning for Machine TranslationDeep Learning for Machine Translation
Deep Learning for Machine Translation
 
Tamil Morphological Analysis
Tamil Morphological AnalysisTamil Morphological Analysis
Tamil Morphological Analysis
 
Language models
Language modelsLanguage models
Language models
 
1909 BERT: why-and-how (CODE SEMINAR)
1909 BERT: why-and-how (CODE SEMINAR)1909 BERT: why-and-how (CODE SEMINAR)
1909 BERT: why-and-how (CODE SEMINAR)
 
Machine translation with statistical approach
Machine translation with statistical approachMachine translation with statistical approach
Machine translation with statistical approach
 
Word embedding
Word embedding Word embedding
Word embedding
 
Equirs: Explicitly Query Understanding Information Retrieval System Based on Hmm
Equirs: Explicitly Query Understanding Information Retrieval System Based on HmmEquirs: Explicitly Query Understanding Information Retrieval System Based on Hmm
Equirs: Explicitly Query Understanding Information Retrieval System Based on Hmm
 
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
 

Semelhante a Integration of speech recognition with computer assisted translation

Error Analysis of Rule-based Machine Translation Outputs
Error Analysis of Rule-based Machine Translation OutputsError Analysis of Rule-based Machine Translation Outputs
Error Analysis of Rule-based Machine Translation Outputs
Parisa Niksefat
 

Semelhante a Integration of speech recognition with computer assisted translation (20)

Translationusing moses1
Translationusing moses1Translationusing moses1
Translationusing moses1
 
A NEURAL MACHINE LANGUAGE TRANSLATION SYSTEM FROM GERMAN TO ENGLISH
A NEURAL MACHINE LANGUAGE TRANSLATION SYSTEM FROM GERMAN TO ENGLISHA NEURAL MACHINE LANGUAGE TRANSLATION SYSTEM FROM GERMAN TO ENGLISH
A NEURAL MACHINE LANGUAGE TRANSLATION SYSTEM FROM GERMAN TO ENGLISH
 
What is machine translation
What is machine translationWhat is machine translation
What is machine translation
 
Searching for the Best Machine Translation Combination
Searching for the Best Machine Translation CombinationSearching for the Best Machine Translation Combination
Searching for the Best Machine Translation Combination
 
Error Analysis of Rule-based Machine Translation Outputs
Error Analysis of Rule-based Machine Translation OutputsError Analysis of Rule-based Machine Translation Outputs
Error Analysis of Rule-based Machine Translation Outputs
 
Speech To Speech Translation
Speech To Speech TranslationSpeech To Speech Translation
Speech To Speech Translation
 
Named Entity Recognition using Hidden Markov Model (HMM)
Named Entity Recognition using Hidden Markov Model (HMM)Named Entity Recognition using Hidden Markov Model (HMM)
Named Entity Recognition using Hidden Markov Model (HMM)
 
Named Entity Recognition using Hidden Markov Model (HMM)
Named Entity Recognition using Hidden Markov Model (HMM)Named Entity Recognition using Hidden Markov Model (HMM)
Named Entity Recognition using Hidden Markov Model (HMM)
 
Named Entity Recognition using Hidden Markov Model (HMM)
Named Entity Recognition using Hidden Markov Model (HMM)Named Entity Recognition using Hidden Markov Model (HMM)
Named Entity Recognition using Hidden Markov Model (HMM)
 
NLP,expert,robotics.pptx
NLP,expert,robotics.pptxNLP,expert,robotics.pptx
NLP,expert,robotics.pptx
 
Experiments with Different Models of Statistcial Machine Translation
Experiments with Different Models of Statistcial Machine TranslationExperiments with Different Models of Statistcial Machine Translation
Experiments with Different Models of Statistcial Machine Translation
 
project present
project presentproject present
project present
 
Machine Tanslation
Machine TanslationMachine Tanslation
Machine Tanslation
 
team10.ppt.pptx
team10.ppt.pptxteam10.ppt.pptx
team10.ppt.pptx
 
Meta-evaluation of machine translation evaluation methods
Meta-evaluation of machine translation evaluation methodsMeta-evaluation of machine translation evaluation methods
Meta-evaluation of machine translation evaluation methods
 
LLM.pdf
LLM.pdfLLM.pdf
LLM.pdf
 
A Novel Approach for Rule Based Translation of English to Marathi
A Novel Approach for Rule Based Translation of English to MarathiA Novel Approach for Rule Based Translation of English to Marathi
A Novel Approach for Rule Based Translation of English to Marathi
 
A Novel Approach for Rule Based Translation of English to Marathi
A Novel Approach for Rule Based Translation of English to MarathiA Novel Approach for Rule Based Translation of English to Marathi
A Novel Approach for Rule Based Translation of English to Marathi
 
A Novel Approach for Rule Based Translation of English to Marathi
A Novel Approach for Rule Based Translation of English to MarathiA Novel Approach for Rule Based Translation of English to Marathi
A Novel Approach for Rule Based Translation of English to Marathi
 
Deciphering voice of customer through speech analytics
Deciphering voice of customer through speech analyticsDeciphering voice of customer through speech analytics
Deciphering voice of customer through speech analytics
 

Último

Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Victor Rentea
 

Último (20)

How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontology
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital Adaptability
 
JohnPollard-hybrid-app-RailsConf2024.pptx
JohnPollard-hybrid-app-RailsConf2024.pptxJohnPollard-hybrid-app-RailsConf2024.pptx
JohnPollard-hybrid-app-RailsConf2024.pptx
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
AI in Action: Real World Use Cases by Anitaraj
AI in Action: Real World Use Cases by AnitarajAI in Action: Real World Use Cases by Anitaraj
AI in Action: Real World Use Cases by Anitaraj
 
Spring Boot vs Quarkus the ultimate battle - DevoxxUK
Spring Boot vs Quarkus the ultimate battle - DevoxxUKSpring Boot vs Quarkus the ultimate battle - DevoxxUK
Spring Boot vs Quarkus the ultimate battle - DevoxxUK
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
Vector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptxVector Search -An Introduction in Oracle Database 23ai.pptx
Vector Search -An Introduction in Oracle Database 23ai.pptx
 
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 

Integration of speech recognition with computer assisted translation

  • 1. 1 Integration of Speech Recognition with Computer Assisted Translation CHAMANI SHIRANTHIKA UNIVERSITY OF MORATUWA SRI LANKA
  • 2.  Introduction  What is Machine Translation (MT)  What is Computer Assisted Translation (CAT)  Technology adapted by CAT and MT  Technology adapted by Automatic Speech Recognition (ASR)  ASR and CAT integration  Translation Quality Evaluation  New Trends in Machine Translation  Conclusion Overview 2
  • 3. Introduction  Researches have been undertaken to implement translation tools with out a use of human translator to increase translation quality and to reduce human post editing needed  Speech is the most natural , practical , simplest and efficient method of human communication  Integration of Speech to translation process is a wide research area  As a solution for blind people for the communication with different languages 3
  • 4.  Sub categories of Computational Linguistics  Computational linguistics is the branch of linguistics in which the techniques of computer science are applied to the analysis and synthesis of language and speech  Machine Translation is accomplished by feeding a text to a computer algorithm that automatically translates in to another language. That is there is no human involvement  Computer Assisted Translation is human translation carried out with the aid of computerized tools What is MT & CAT 4
  • 6.  A rule based machine translation system consists of collection of rules called grammar rules, lexicon and software programs to process the rules  Focus on syntactic, semantic and morphological details of both the source language and the translated language when translating • Syntactic – how words are grammatically arranged in sentences, how we speech in communication • Semantic – how words are meaningfully arranged in sentences • Morphological – structure of sentences, source and targeted language Rule Based Machine Translation 6
  • 7. Rule Based Machine Translation (continued..) Structure of the Rule Based Machine Translation system • A tree structure is used to represent the structure of the sentence • A typical English sentence consists of two major parts as the noun phrase (NP) & the verb phrase (VP) • These two can be further divided • Following are the rules to represent a simple grammar S -> NPVP VP -> VNP NP -> Name NP -> ART N S stands for sentence, V for verb, N for noun and ART for article • Example : Saman was happy can be written in logical form as (< PAST HAPPY> (NAME “Saman”)) 7
  • 8.  Translation based on previous example translations as results of experiments  Uses knowledge sources to support the translation process  Require bilingual content  Two types • Statistical Machine Translation • Example Based Machine Translation Empirical Based Machine Translation 8
  • 9. Statistical Machine Translation  Translations based on statistical models  Statistical Translation Model – Learned from Bilingual Data (TM) • Probabilistic mapping of equivalencies in source words and phrases with target languag e words and phrases through the Unsupervised Expected Model (EM) training and word and phrase alignment process • Generates a lots of possible translations • Includes finite state models such as finite state transducers , alignment models and phrase based models  Statistical Language Model – Learned from Monolingual Target Language Data • Probabilistic model of relative fluency and general usage patterns in the target language • Based on n-gram model • Target language model selects the “best” translations from a list of possible candidates • Candidates stored in a N-best list • Concept of re-ranking 9
  • 10. • N-gram is a contiguous sequence of n items from a given sequence of text or speech • When the items are words, n-grams are also called as shingles • An n-gram of size 1 is a “unigram” , size 2 is a “bigram” , size 3 is “trigram” and so on..  Advantages : More efficient use of human and data resources Disadvantages in rule based approach are eliminated  Disadvantages : Corpus creation can be costly Errors are hard to predict and fix Examples : SYSTRAN, ART, METEO, LOGOS, Anusaarka, TC- Star, Google translate Statistical Machine Translation (continued..) 10
  • 11. What is Speech Recognition ?  Speech Recognition is the translation of spoken words into text  Also called “Automatic Speech Recognition” (ASR), “Computer Speech Recognition” or just “Speech To Text” (STT) 11
  • 13. Machine Learning paradigms for speech recognition • Hidden Markov Model • Discriminative Learning • Structured Sequence Learning • Bayesian Learning • Adaptive Learning • Multi – task Learning • Active Learning 13
  • 14. Speech recognition systems • Google Speech API • Cloud Speech API • Microsoft cognitive services – Bing speech API • API.AI • Speechmatics • Vocapia Speech to Text API • Klaldi • iSpeech • Baidu • Siri • Hound • Google Now 14
  • 15. Integration of ASR & MT 4 approaches  Word graphs product – Separate large word graphs for ASR and MT system will be generated and take the product of these using composition operation in automata theory  ASR constrained search – Replaced n-gram language model of phrase base MT with the ASR word graph  Adapted Language Model – MT system has been improved by adopting it’s language model to the ASR output  MT-Derived Language Model – Rescoring the ASR word graph with a language model that is derived from the MT system Examples : TELNET, IBM 1,2 Models , SEECAT 15
  • 16. Combined ASR / SMT Model P(e) Language Model P(f|e) Translation Model P(x|e) Acoustic Model e = argmax {P(e). P(f|e).P(x|e)} e: Target Language Text x: Speechf: Source Language 16
  • 17. Loose Integration & Tight Integration approaches Loose Integration approach • P(e) has 2 components • PS(e) – characterizes those aspects of language that can be acquired from large t ext corpora in the target language • PM(e) – represents the effects that can be acquired from the source language text P(e) = (λM) PM(e) + (λS) PS(e) Assumption :- These 2 models are independent P(e) = (λM) PM(e) . (λS) PS(e) P(e) = PM(e) λM. PS(e) λS 17
  • 18. Tight Integration approach • Involves using SMT to reevaluate ASR hypothesis • Each string hypothesis appearing in the ASR N-best list is rescored using the language translation probability, P(f|e) obtained from the SMT • The score for each string is combined from a log linear combination of acoustic, language model & translation model probabilities e = argmaxe { (λ1) log(P(e)) + (λ2) log(P(f|e)) + (λ3) log(P(x|e)) } 18
  • 19. Translation Quality Evaluation  TWER or edit distance  CSR  BLEU  KSR  MAR  SER  F – Measure  TER Scores 19
  • 20. New trends in Machine Translation • Neural MT • Google Translate -> Phrase based which breaks an input sentence into words and phrases to be translated largely independently • GNMT -> considers the entire input sentence as a unit for translation • Map the meaning of a sentence into a fixed-length vector representation and then generate a translation based on that vector • Advantages over Google Translate ---  it requires fewer engineering design choices  Easier to build and train  Small memory footprint  Generalize well to long sequences 20
  • 21. GNMT translating a Chinese sentence to English 21
  • 22. Neural MT of Microsoft 22 Encode Encode Encode Final Output Matrix Attention Layer 500 dimension vector 1000 dimension vector
  • 23. ASR – MT System of Microsoft 23 Automatic Speech Recognition True Text Machine Translation Text To Speech
  • 24. MT in 2017 (Some popular and publicly available commercial systems) • Microsoft • Microsoft Adapted • Systran Neural • SDL • SDL Adapted • Lilt • Lilt Adapted • Lilt Interactive • A/B Testing • Convergence of TM and MT Systems • Adoption of MT for instant web publishing • NMT + SMT/RBMT approach • NMT for mobile devices 24
  • 25. Deep learning in to MT Attention Mechanism • NMT translates the whole sentence at once • Able to translate very long sentences • Attention retains a memory of source hidden states (Random Access Memory) • Compare target and source hidden states • Learning both translation & alignment • Local attention & Global attention 25
  • 26. Conclusion  Implemented models are still in developing era  Statistical approaches and language models have been popularized so far  Speech recognition tools have been developed so far  Concept of AI , ML can be integrated Future works  Approaches to minimize the human post editing in translation  Increase the quality of available translation tools  Enhance the effectiveness of speech recognition paradigm  A method of communication with other languages, for blind people so that they can enter a speech input and can get responses in their language by means of speech to text conversion 26
  • 27. 27