SlideShare ist ein Scribd-Unternehmen logo
1 von 1
Downloaden Sie, um offline zu lesen
Training Data Simulation:
The neural system combination framework should be
trained on the outputs of multiple translation systems
and the gold target translations. In order to keep
consistency in training and testing, we design a strategy
to simulate the real scenario.
Figure 2: Strategy of training data simulation
Data sets: 2.08M sentence pairs of Chinese‐English
extracted from LDC corpus.
Systems: we compare our neural combination system
with the best individual engines, and the state‐of‐the‐art
traditional combination system Jane.
Table 2: Translation results (BLEU score) for different machine
translation and system combination methods. Jane is an open source
system combination toolkit that uses confusion network decoding.
Figure 3: Comparison of translation fluency (word order), according to
the automatic evaluation metrics RIBES.
 The proposed neural system combination method
using hierarchical attentional seq2seq model can
substantially improve the translation quality by
combining the merits of SMT and NMT.
 Neural system combination architecture is simple and
can be applied into other applications, such as
summarization and text generation.
Neural machine translation (NMT) generates much
more fluent results compared to statistical machine
translation (SMT). However, SMT is usually better than
NMT in translation adequacy. System combination is
therefore a promising direction to unify the advantages
of both NMT and SMT.
Our solution: Neural System Combination (NSC)
 Step 1: for a source sentence, generate translations
with phrase‐based SMT (PBMT), hierarchical phrase‐
based SMT (HPMT) and NMT.
 Step 2: design a multi‐source sequence‐to‐sequence
model that takes as input the three translation results
of PBMT, HPMT and NMT, and produces the final
target language translation.
Translation Example:
Table 1: Translation examples of single system and our model.
Inputs: translation outputs of PBMT, HPMT and NMT.
Outputs: final target language translation results.
Core idea: hierarchical attention‐based multi‐source
seq2seq model.
Figure 1: The architecture of neural system combination model
Layer I Attention:
where scores how well
and match.
Layer II Attention:
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
Neural System Combination for Machine Transaltion
Long Zhou, Wenpeng Hu, Jiajun Zhang and Chengqing Zong
{long.zhou, wenpeng.hu , jjzhang, cqzong}@nlpr.ia.ac.cn
Overview of our  approach
Experiments
Conclusions
Background and Motivation
System MT03 MT04 MT05 MT06 Ave
PBMT 37.47 41.20 36.41 36.03 37.78
HPMT 38.05 41.47 36.86 36.04 38.10
NMT 37.91 38.95 36.02 36.65 37.38
Jane 39.83 42.75 38.63 39.10 40.08
NSC 40.64 44.81 38.80 38.26 40.63
NSC+Source 42.16 45.51 40.28 39.02 41.75
NSC+Ensemble 41.67 45.95 40.37 39.02 41.75
NSC+Source+Ensemble 43.55 47.09 42.02 41.10 43.44
1h

2h

h nm

...
2h

h nm

...
1h

1
n
z 2
n
z n
n
mz...
1h

2h

h pm

...
2h

h pm

...
1h

1
p
z 2
p
z p
p
mz...
1h

2h

h hm

...
2h

h hm

...
1h

1
h
z 2
h
z h
h
mz...
-1jS jS 1jS 
 -1jS
1jy  jy
 jS
1jy 

...

... ...1
n
j 2
p
j1
p
j p
jm
1j 2j 3j

2
n
j
n
jm 2
h
j1
h
j h
jm
jnc
jpc jhc

... ...
jc
:n
Z :p
Z :h
Z
1
m
k
jk ji i
i
c h

 
1
exp( )
exp( )
jik
ji m
jll
e
e




1tanh( )T
jji a a a ie v W s U h % 1js 
%
ih
1
K
j jk jk
k
c c

  ''
1
1
exp( )
exp( )
j jk
jk
j
jkk
s c
s c






%
%
Source: 海珊 也 与 恐怖 组织网 建立 了 联系 。
Pinyin: hanshan ye yu kongbu zuzhiwang jianli le lianxi 。
Ref.: hussein has also established ties with terrorist networks.
PBMT: hussein also has established relations and terrorist group .
HPMT: hussein also and terrorist group established relations .
NMT: hussein also established relations with <UNK> .
NSC: hussein also has established relations with the terrorist group .
All corpus
(source, target)
Corpus B
Corpus A
PBMT
train
train
Translate
corpus B
Translate
corpus A
Translations of
corpus B
Translations of
corpus A
MT
translations
Randomly
divide
Randomly
divide
HPMT
NMT
PBMT
HPMT
NMT
Training data for neural system combination model
78
79
80
81
82
83
84
PBMT HPMT NMT Jane NSC +Source +Ensemble
RIBES

Weitere ähnliche Inhalte

Was ist angesagt?

Neural network
Neural networkNeural network
Neural network
Saddam Hussain
 
Forecasting of Sales using Neural network techniques
Forecasting of Sales using Neural network techniquesForecasting of Sales using Neural network techniques
Forecasting of Sales using Neural network techniques
Hitesh Dua
 

Was ist angesagt? (20)

ANN load forecasting
ANN load forecastingANN load forecasting
ANN load forecasting
 
A Time Series ANN Approach for Weather Forecasting
A Time Series ANN Approach for Weather ForecastingA Time Series ANN Approach for Weather Forecasting
A Time Series ANN Approach for Weather Forecasting
 
Neural network
Neural networkNeural network
Neural network
 
Optimization as a model for few shot learning
Optimization as a model for few shot learningOptimization as a model for few shot learning
Optimization as a model for few shot learning
 
Learning to compare: relation network for few shot learning
Learning to compare: relation network for few shot learningLearning to compare: relation network for few shot learning
Learning to compare: relation network for few shot learning
 
Face Recognition Using Neural Networks
Face Recognition Using Neural NetworksFace Recognition Using Neural Networks
Face Recognition Using Neural Networks
 
01 Introduction to Machine Learning
01 Introduction to Machine Learning01 Introduction to Machine Learning
01 Introduction to Machine Learning
 
AI IEEE
AI IEEEAI IEEE
AI IEEE
 
Meta learning with memory augmented neural network
Meta learning with memory augmented neural networkMeta learning with memory augmented neural network
Meta learning with memory augmented neural network
 
Artificial neural network for load forecasting in smart grid
Artificial neural network for load forecasting in smart gridArtificial neural network for load forecasting in smart grid
Artificial neural network for load forecasting in smart grid
 
Artificial Neural Networks - ANN
Artificial Neural Networks - ANNArtificial Neural Networks - ANN
Artificial Neural Networks - ANN
 
Handwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPTHandwritten Digit Recognition(Convolutional Neural Network) PPT
Handwritten Digit Recognition(Convolutional Neural Network) PPT
 
Presentation, navid khoob
Presentation, navid khoobPresentation, navid khoob
Presentation, navid khoob
 
Neural network
Neural network Neural network
Neural network
 
Forecasting of Sales using Neural network techniques
Forecasting of Sales using Neural network techniquesForecasting of Sales using Neural network techniques
Forecasting of Sales using Neural network techniques
 
Few shot learning/ one shot learning/ machine learning
Few shot learning/ one shot learning/ machine learningFew shot learning/ one shot learning/ machine learning
Few shot learning/ one shot learning/ machine learning
 
Artificial neural network for machine learning
Artificial neural network for machine learningArtificial neural network for machine learning
Artificial neural network for machine learning
 
Artificial Neural Network(Artificial intelligence)
Artificial Neural Network(Artificial intelligence)Artificial Neural Network(Artificial intelligence)
Artificial Neural Network(Artificial intelligence)
 
test
testtest
test
 
02 Fundamental Concepts of ANN
02 Fundamental Concepts of ANN02 Fundamental Concepts of ANN
02 Fundamental Concepts of ANN
 

Ähnlich wie Long Zhou - 2017 - Neural System Combination for Machine Transaltion

Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...
Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...
Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...
CSCJournals
 
Predictive Metabonomics
Predictive MetabonomicsPredictive Metabonomics
Predictive Metabonomics
Marilyn Arceo
 
AN IMPROVED METHOD FOR IDENTIFYING WELL-TEST INTERPRETATION MODEL BASED ON AG...
AN IMPROVED METHOD FOR IDENTIFYING WELL-TEST INTERPRETATION MODEL BASED ON AG...AN IMPROVED METHOD FOR IDENTIFYING WELL-TEST INTERPRETATION MODEL BASED ON AG...
AN IMPROVED METHOD FOR IDENTIFYING WELL-TEST INTERPRETATION MODEL BASED ON AG...
IAEME Publication
 

Ähnlich wie Long Zhou - 2017 - Neural System Combination for Machine Transaltion (20)

Black-box modeling of nonlinear system using evolutionary neural NARX model
Black-box modeling of nonlinear system using evolutionary neural NARX modelBlack-box modeling of nonlinear system using evolutionary neural NARX model
Black-box modeling of nonlinear system using evolutionary neural NARX model
 
CONTRAST OF RESNET AND DENSENET BASED ON THE RECOGNITION OF SIMPLE FRUIT DATA...
CONTRAST OF RESNET AND DENSENET BASED ON THE RECOGNITION OF SIMPLE FRUIT DATA...CONTRAST OF RESNET AND DENSENET BASED ON THE RECOGNITION OF SIMPLE FRUIT DATA...
CONTRAST OF RESNET AND DENSENET BASED ON THE RECOGNITION OF SIMPLE FRUIT DATA...
 
6119ijcsitce01
6119ijcsitce016119ijcsitce01
6119ijcsitce01
 
CONTRAST OF RESNET AND DENSENET BASED ON THE RECOGNITION OF SIMPLE FRUIT DATA...
CONTRAST OF RESNET AND DENSENET BASED ON THE RECOGNITION OF SIMPLE FRUIT DATA...CONTRAST OF RESNET AND DENSENET BASED ON THE RECOGNITION OF SIMPLE FRUIT DATA...
CONTRAST OF RESNET AND DENSENET BASED ON THE RECOGNITION OF SIMPLE FRUIT DATA...
 
Comparison of Neural Network Training Functions for Hematoma Classification i...
Comparison of Neural Network Training Functions for Hematoma Classification i...Comparison of Neural Network Training Functions for Hematoma Classification i...
Comparison of Neural Network Training Functions for Hematoma Classification i...
 
Downloadfile
DownloadfileDownloadfile
Downloadfile
 
F017533540
F017533540F017533540
F017533540
 
Artificial Neural Network and Multi-Response Optimization in Reliability Meas...
Artificial Neural Network and Multi-Response Optimization in Reliability Meas...Artificial Neural Network and Multi-Response Optimization in Reliability Meas...
Artificial Neural Network and Multi-Response Optimization in Reliability Meas...
 
MLConf 2013: Metronome and Parallel Iterative Algorithms on YARN
MLConf 2013: Metronome and Parallel Iterative Algorithms on YARNMLConf 2013: Metronome and Parallel Iterative Algorithms on YARN
MLConf 2013: Metronome and Parallel Iterative Algorithms on YARN
 
Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...
Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...
Comparison Between Levenberg-Marquardt And Scaled Conjugate Gradient Training...
 
M010237578
M010237578M010237578
M010237578
 
Architecture neural network deep optimizing based on self organizing feature ...
Architecture neural network deep optimizing based on self organizing feature ...Architecture neural network deep optimizing based on self organizing feature ...
Architecture neural network deep optimizing based on self organizing feature ...
 
PPT
PPTPPT
PPT
 
A Learning Linguistic Teaching Control for a Multi-Area Electric Power System
A Learning Linguistic Teaching Control for a Multi-Area Electric Power SystemA Learning Linguistic Teaching Control for a Multi-Area Electric Power System
A Learning Linguistic Teaching Control for a Multi-Area Electric Power System
 
A Simple Segmentation Approach for Unconstrained Cursive Handwritten Words in...
A Simple Segmentation Approach for Unconstrained Cursive Handwritten Words in...A Simple Segmentation Approach for Unconstrained Cursive Handwritten Words in...
A Simple Segmentation Approach for Unconstrained Cursive Handwritten Words in...
 
I0343047049
I0343047049I0343047049
I0343047049
 
N ns 1
N ns 1N ns 1
N ns 1
 
IRJET-Performance Enhancement in Machine Learning System using Hybrid Bee Col...
IRJET-Performance Enhancement in Machine Learning System using Hybrid Bee Col...IRJET-Performance Enhancement in Machine Learning System using Hybrid Bee Col...
IRJET-Performance Enhancement in Machine Learning System using Hybrid Bee Col...
 
Predictive Metabonomics
Predictive MetabonomicsPredictive Metabonomics
Predictive Metabonomics
 
AN IMPROVED METHOD FOR IDENTIFYING WELL-TEST INTERPRETATION MODEL BASED ON AG...
AN IMPROVED METHOD FOR IDENTIFYING WELL-TEST INTERPRETATION MODEL BASED ON AG...AN IMPROVED METHOD FOR IDENTIFYING WELL-TEST INTERPRETATION MODEL BASED ON AG...
AN IMPROVED METHOD FOR IDENTIFYING WELL-TEST INTERPRETATION MODEL BASED ON AG...
 

Mehr von Association for Computational Linguistics

Mehr von Association for Computational Linguistics (20)

Muis - 2016 - Weak Semi-Markov CRFs for NP Chunking in Informal Text
Muis - 2016 - Weak Semi-Markov CRFs for NP Chunking in Informal TextMuis - 2016 - Weak Semi-Markov CRFs for NP Chunking in Informal Text
Muis - 2016 - Weak Semi-Markov CRFs for NP Chunking in Informal Text
 
Castro - 2018 - A High Coverage Method for Automatic False Friends Detection ...
Castro - 2018 - A High Coverage Method for Automatic False Friends Detection ...Castro - 2018 - A High Coverage Method for Automatic False Friends Detection ...
Castro - 2018 - A High Coverage Method for Automatic False Friends Detection ...
 
Castro - 2018 - A Crowd-Annotated Spanish Corpus for Humour Analysis
Castro - 2018 - A Crowd-Annotated Spanish Corpus for Humour AnalysisCastro - 2018 - A Crowd-Annotated Spanish Corpus for Humour Analysis
Castro - 2018 - A Crowd-Annotated Spanish Corpus for Humour Analysis
 
Muthu Kumar Chandrasekaran - 2018 - Countering Position Bias in Instructor In...
Muthu Kumar Chandrasekaran - 2018 - Countering Position Bias in Instructor In...Muthu Kumar Chandrasekaran - 2018 - Countering Position Bias in Instructor In...
Muthu Kumar Chandrasekaran - 2018 - Countering Position Bias in Instructor In...
 
Daniel Gildea - 2018 - The ACL Anthology: Current State and Future Directions
Daniel Gildea - 2018 - The ACL Anthology: Current State and Future DirectionsDaniel Gildea - 2018 - The ACL Anthology: Current State and Future Directions
Daniel Gildea - 2018 - The ACL Anthology: Current State and Future Directions
 
Elior Sulem - 2018 - Semantic Structural Evaluation for Text Simplification
Elior Sulem - 2018 - Semantic Structural Evaluation for Text SimplificationElior Sulem - 2018 - Semantic Structural Evaluation for Text Simplification
Elior Sulem - 2018 - Semantic Structural Evaluation for Text Simplification
 
Daniel Gildea - 2018 - The ACL Anthology: Current State and Future Directions
Daniel Gildea - 2018 - The ACL Anthology: Current State and Future DirectionsDaniel Gildea - 2018 - The ACL Anthology: Current State and Future Directions
Daniel Gildea - 2018 - The ACL Anthology: Current State and Future Directions
 
Wenqiang Lei - 2018 - Sequicity: Simplifying Task-oriented Dialogue Systems w...
Wenqiang Lei - 2018 - Sequicity: Simplifying Task-oriented Dialogue Systems w...Wenqiang Lei - 2018 - Sequicity: Simplifying Task-oriented Dialogue Systems w...
Wenqiang Lei - 2018 - Sequicity: Simplifying Task-oriented Dialogue Systems w...
 
Matthew Marge - 2017 - Exploring Variation of Natural Human Commands to a Rob...
Matthew Marge - 2017 - Exploring Variation of Natural Human Commands to a Rob...Matthew Marge - 2017 - Exploring Variation of Natural Human Commands to a Rob...
Matthew Marge - 2017 - Exploring Variation of Natural Human Commands to a Rob...
 
Venkatesh Duppada - 2017 - SeerNet at EmoInt-2017: Tweet Emotion Intensity Es...
Venkatesh Duppada - 2017 - SeerNet at EmoInt-2017: Tweet Emotion Intensity Es...Venkatesh Duppada - 2017 - SeerNet at EmoInt-2017: Tweet Emotion Intensity Es...
Venkatesh Duppada - 2017 - SeerNet at EmoInt-2017: Tweet Emotion Intensity Es...
 
Satoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 Workshop
Satoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 WorkshopSatoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 Workshop
Satoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 Workshop
 
Chenchen Ding - 2015 - NICT at WAT 2015
Chenchen Ding - 2015 - NICT at WAT 2015Chenchen Ding - 2015 - NICT at WAT 2015
Chenchen Ding - 2015 - NICT at WAT 2015
 
John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...
John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...
John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...
 
John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...
John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...
John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...
 
Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...
Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...
Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...
 
Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...
Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...
Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...
 
Hyoung-Gyu Lee - 2015 - NAVER Machine Translation System for WAT 2015
Hyoung-Gyu Lee - 2015 - NAVER Machine Translation System for WAT 2015Hyoung-Gyu Lee - 2015 - NAVER Machine Translation System for WAT 2015
Hyoung-Gyu Lee - 2015 - NAVER Machine Translation System for WAT 2015
 
Satoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 Workshop
Satoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 WorkshopSatoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 Workshop
Satoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 Workshop
 
Chenchen Ding - 2015 - NICT at WAT 2015
Chenchen Ding - 2015 - NICT at WAT 2015Chenchen Ding - 2015 - NICT at WAT 2015
Chenchen Ding - 2015 - NICT at WAT 2015
 
Graham Neubig - 2015 - Neural Reranking Improves Subjective Quality of Machin...
Graham Neubig - 2015 - Neural Reranking Improves Subjective Quality of Machin...Graham Neubig - 2015 - Neural Reranking Improves Subjective Quality of Machin...
Graham Neubig - 2015 - Neural Reranking Improves Subjective Quality of Machin...
 

Kürzlich hochgeladen

Kürzlich hochgeladen (20)

TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
 
Sensory_Experience_and_Emotional_Resonance_in_Gabriel_Okaras_The_Piano_and_Th...
Sensory_Experience_and_Emotional_Resonance_in_Gabriel_Okaras_The_Piano_and_Th...Sensory_Experience_and_Emotional_Resonance_in_Gabriel_Okaras_The_Piano_and_Th...
Sensory_Experience_and_Emotional_Resonance_in_Gabriel_Okaras_The_Piano_and_Th...
 
How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibit
 
Wellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxWellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptx
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024
 
How to Add New Custom Addons Path in Odoo 17
How to Add New Custom Addons Path in Odoo 17How to Add New Custom Addons Path in Odoo 17
How to Add New Custom Addons Path in Odoo 17
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
REMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptxREMIFENTANIL: An Ultra short acting opioid.pptx
REMIFENTANIL: An Ultra short acting opioid.pptx
 
Google Gemini An AI Revolution in Education.pptx
Google Gemini An AI Revolution in Education.pptxGoogle Gemini An AI Revolution in Education.pptx
Google Gemini An AI Revolution in Education.pptx
 
Towards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptxTowards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptx
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and Modifications
 
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
80 ĐỀ THI THỬ TUYỂN SINH TIẾNG ANH VÀO 10 SỞ GD – ĐT THÀNH PHỐ HỒ CHÍ MINH NĂ...
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdf
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)
 
Python Notes for mca i year students osmania university.docx
Python Notes for mca i year students osmania university.docxPython Notes for mca i year students osmania university.docx
Python Notes for mca i year students osmania university.docx
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17
 
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptxHMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
 

Long Zhou - 2017 - Neural System Combination for Machine Transaltion

  • 1. Training Data Simulation: The neural system combination framework should be trained on the outputs of multiple translation systems and the gold target translations. In order to keep consistency in training and testing, we design a strategy to simulate the real scenario. Figure 2: Strategy of training data simulation Data sets: 2.08M sentence pairs of Chinese‐English extracted from LDC corpus. Systems: we compare our neural combination system with the best individual engines, and the state‐of‐the‐art traditional combination system Jane. Table 2: Translation results (BLEU score) for different machine translation and system combination methods. Jane is an open source system combination toolkit that uses confusion network decoding. Figure 3: Comparison of translation fluency (word order), according to the automatic evaluation metrics RIBES.  The proposed neural system combination method using hierarchical attentional seq2seq model can substantially improve the translation quality by combining the merits of SMT and NMT.  Neural system combination architecture is simple and can be applied into other applications, such as summarization and text generation. Neural machine translation (NMT) generates much more fluent results compared to statistical machine translation (SMT). However, SMT is usually better than NMT in translation adequacy. System combination is therefore a promising direction to unify the advantages of both NMT and SMT. Our solution: Neural System Combination (NSC)  Step 1: for a source sentence, generate translations with phrase‐based SMT (PBMT), hierarchical phrase‐ based SMT (HPMT) and NMT.  Step 2: design a multi‐source sequence‐to‐sequence model that takes as input the three translation results of PBMT, HPMT and NMT, and produces the final target language translation. Translation Example: Table 1: Translation examples of single system and our model. Inputs: translation outputs of PBMT, HPMT and NMT. Outputs: final target language translation results. Core idea: hierarchical attention‐based multi‐source seq2seq model. Figure 1: The architecture of neural system combination model Layer I Attention: where scores how well and match. Layer II Attention: National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Neural System Combination for Machine Transaltion Long Zhou, Wenpeng Hu, Jiajun Zhang and Chengqing Zong {long.zhou, wenpeng.hu , jjzhang, cqzong}@nlpr.ia.ac.cn Overview of our  approach Experiments Conclusions Background and Motivation System MT03 MT04 MT05 MT06 Ave PBMT 37.47 41.20 36.41 36.03 37.78 HPMT 38.05 41.47 36.86 36.04 38.10 NMT 37.91 38.95 36.02 36.65 37.38 Jane 39.83 42.75 38.63 39.10 40.08 NSC 40.64 44.81 38.80 38.26 40.63 NSC+Source 42.16 45.51 40.28 39.02 41.75 NSC+Ensemble 41.67 45.95 40.37 39.02 41.75 NSC+Source+Ensemble 43.55 47.09 42.02 41.10 43.44 1h  2h  h nm  ... 2h  h nm  ... 1h  1 n z 2 n z n n mz... 1h  2h  h pm  ... 2h  h pm  ... 1h  1 p z 2 p z p p mz... 1h  2h  h hm  ... 2h  h hm  ... 1h  1 h z 2 h z h h mz... -1jS jS 1jS   -1jS 1jy  jy  jS 1jy   ...  ... ...1 n j 2 p j1 p j p jm 1j 2j 3j  2 n j n jm 2 h j1 h j h jm jnc jpc jhc  ... ... jc :n Z :p Z :h Z 1 m k jk ji i i c h    1 exp( ) exp( ) jik ji m jll e e     1tanh( )T jji a a a ie v W s U h % 1js  % ih 1 K j jk jk k c c    '' 1 1 exp( ) exp( ) j jk jk j jkk s c s c       % % Source: 海珊 也 与 恐怖 组织网 建立 了 联系 。 Pinyin: hanshan ye yu kongbu zuzhiwang jianli le lianxi 。 Ref.: hussein has also established ties with terrorist networks. PBMT: hussein also has established relations and terrorist group . HPMT: hussein also and terrorist group established relations . NMT: hussein also established relations with <UNK> . NSC: hussein also has established relations with the terrorist group . All corpus (source, target) Corpus B Corpus A PBMT train train Translate corpus B Translate corpus A Translations of corpus B Translations of corpus A MT translations Randomly divide Randomly divide HPMT NMT PBMT HPMT NMT Training data for neural system combination model 78 79 80 81 82 83 84 PBMT HPMT NMT Jane NSC +Source +Ensemble RIBES