SlideShare a Scribd company logo
1 of 15
Download to read offline
Exploiting	Source-side	Monolingual	Data	
in	Neural	Machine	Translation	
Jiajun Zhang,	Chengqing Zong
EMNLP2016
presentation
Sekizawa Yuuki
2017/10/30 1
Exploiting	Source-side	Monolingual	Data	in	
Neural	Machine	Translation	
• The	source-side	monolingual	data	is	not	fully	explored
• (especially	parallel	corpus	is	far	from	sufficient)	
• propose	two	approaches
1. employ	the	self-learning	algorithm	to	generate	the	synthetic	
large-scale	parallel	data	for	NMT	training.	
2. apply	the	multi-task	learning	framework	using	two	NMTs
• predict	the	translation	and	the	reordered	source-side	
monolingual	sentences	simultaneously.	
• proposed	methods	obtain	significant	improvements
over	the	strong	attention-based	NMT.	
2017/10/30 2
NMT(Bahdanau+	2014)
2017/10/30 3
previous	work	using	monolingual	data
• SMT
• Koehn	et	al.	(2007)
• Chiang	(2007)	
• NMT
• Gulcehre et	al.	(2015)	target	only
• Sennrich et	al.	(2015)	target	only
• Luong	et	al.	(2015)
2017/10/31 4
• approach1:	self-learning	method	
synthetic	parallel	corpus
(big	enough)
bilingual	corpus
(not	big	enough)
proposed	method	1
2017/10/30 5
source
corpus
target
corpus
1.	MT
training
MT	baseline
source-side
monolingual
corpus	(large)
target-side
translated
corpus
new	NMT	system
3.	NMT	training
using	combined
corpus
self-learning	method
• make	synthetic	bilingual	corpus
• target	parts	may	negatively	influence	the	decoder	model	
• distinguish	original	bitext from	the	synthetic	bilingual	
sentences	during	NMT	training
• freezing	the	parameters	of	the	decoder	network	for	the	
synthetic	data	
2017/10/30 6
proposed	method	2
• approach2:	sentence	reordering	method	
2017/10/30 7
same	encoder
sentence	reordering	method
2017/10/31 8
• reordering
• trained	on	source-side	monolingual	data	(large)	using	NMT
• target-side	is	reordered	source	sentence	
• using	the	pre-ordering	rules	(Wang	et	al.,	2007)	
• translation	(more	attention)
• trained	on	the	sentence	aligned	parallel	data	(small)
• training	:	reordering	à translation	à reordering	à…
one	epoch																					several	epochs
sentence	reordering	method
2017/10/31
• objective	function	(multi-task	learning)	
translation
reordering
parameter	collection
experiment	settings
• language:	Chinese-to-English	translation
• machine	translation	corpus
• small	bilingual	data	:	0.63M	sentence	from	LDC	corpora5	
• validation:	NIST	2003	(MT03)	dataset
• test:		NIST	2004	(MT04),	NIST	2005	(MT05)	and	NIST	2006	
(MT06)	datasets.
• source-side	monolingual	data
• collect	about	20M	Chinese	sentences	from	LDC
• retain	the	6.5M	sentences
• more	than	50%	words	should	appear	in	the	source-side	
portion	of	the	bilingual	training	data	
• ordered	by	the	word	hit	rate.	
2017/10/31 10
experiment	settings
• segmentation
• Chinese:	sentences	Stanford	Word	Segmenter6.	
• English:	Moses	decoder7
• source	sentence’s	parser
• Berkeley	parser	(Petrov et	al.,	2006)
• reordering	method	(Wang	et	al.,	2007)
• training	settings
• remove	all	the	sentences	of	length	over	50	words
• limit	the	vocabulary	in	both	Chinese	and	English	to	the	
most	40K	words	
2017/10/31 11
results	on	BLEU	score
2017/10/31 12
SL:	self-learning	(make	synthetic	bilingual	corpus)
MTL:	multi-task	learning	 (sentence	reordering)
Autoencoder:	multi-task	learning	framework	in	which	a	simple	autoencoder is	
adopted	on	source-side	monolingual	data	(Luong	et	al.,	2015)	
NMT	baseline				à
(Bahdanau+	2014)
Quality	with	amount	of	monolingual	data
2017/10/31 13
experiment	with	large	corpus
2017/10/31 14
The	large-scale	data	set	contains	about	2.1M	sentence	pairs
12M	monolingual	data	set
Exploiting	Source-side	Monolingual	Data	in	
Neural	Machine	Translation	
• The	source-side	monolingual	data	is	not	fully	explored
• (especially	parallel	corpus	is	far	from	sufficient)	
• propose	two	approaches
1. employ	the	self-learning	algorithm	to	generate	the	synthetic	
large-scale	parallel	data	for	NMT	training.	
2. apply	the	multi-task	learning	framework	using	two	NMTs
• predict	the	translation	and	the	reordered	source-side	
monolingual	sentences	simultaneously.	
• proposed	methods	obtain	significant	improvements
over	the	strong	attention-based	NMT.	
2017/11/6 15

More Related Content

Similar to paper introducing: Exploiting source side monolingual data in neural machine translation

Meta-Evaluation of Translation Evaluation Methods: a systematic up-to-date ov...
Meta-Evaluation of Translation Evaluation Methods: a systematic up-to-date ov...Meta-Evaluation of Translation Evaluation Methods: a systematic up-to-date ov...
Meta-Evaluation of Translation Evaluation Methods: a systematic up-to-date ov...
Lifeng (Aaron) Han
 
Biomedical Word Sense Disambiguation presentation [Autosaved]
Biomedical Word Sense Disambiguation presentation [Autosaved]Biomedical Word Sense Disambiguation presentation [Autosaved]
Biomedical Word Sense Disambiguation presentation [Autosaved]
akm sabbir
 
Deep Learning, Where Are You Going?
Deep Learning, Where Are You Going?Deep Learning, Where Are You Going?
Deep Learning, Where Are You Going?
NAVER Engineering
 
Translating phrases in neural machine translation
Translating phrases in neural machine translationTranslating phrases in neural machine translation
Translating phrases in neural machine translation
sekizawayuuki
 

Similar to paper introducing: Exploiting source side monolingual data in neural machine translation (20)

Orchestration Graphs: Enabling Rich Learning Scenarios at Scale
Orchestration Graphs: Enabling Rich Learning Scenarios at ScaleOrchestration Graphs: Enabling Rich Learning Scenarios at Scale
Orchestration Graphs: Enabling Rich Learning Scenarios at Scale
 
2019 dynamically composing_domain-data_selection_with_clean-data_selection_by...
2019 dynamically composing_domain-data_selection_with_clean-data_selection_by...2019 dynamically composing_domain-data_selection_with_clean-data_selection_by...
2019 dynamically composing_domain-data_selection_with_clean-data_selection_by...
 
2010 PACLIC - pay attention to categories
2010 PACLIC - pay attention to categories2010 PACLIC - pay attention to categories
2010 PACLIC - pay attention to categories
 
Meta-Evaluation of Translation Evaluation Methods: a systematic up-to-date ov...
Meta-Evaluation of Translation Evaluation Methods: a systematic up-to-date ov...Meta-Evaluation of Translation Evaluation Methods: a systematic up-to-date ov...
Meta-Evaluation of Translation Evaluation Methods: a systematic up-to-date ov...
 
Philippe Langlais - 2017 - Users and Data: The Two Neglected Children of Bili...
Philippe Langlais - 2017 - Users and Data: The Two Neglected Children of Bili...Philippe Langlais - 2017 - Users and Data: The Two Neglected Children of Bili...
Philippe Langlais - 2017 - Users and Data: The Two Neglected Children of Bili...
 
Biomedical Word Sense Disambiguation presentation [Autosaved]
Biomedical Word Sense Disambiguation presentation [Autosaved]Biomedical Word Sense Disambiguation presentation [Autosaved]
Biomedical Word Sense Disambiguation presentation [Autosaved]
 
Deep Learning for Natural Language Processing
Deep Learning for Natural Language ProcessingDeep Learning for Natural Language Processing
Deep Learning for Natural Language Processing
 
Transfer Learning for Natural Language Processing
Transfer Learning for Natural Language ProcessingTransfer Learning for Natural Language Processing
Transfer Learning for Natural Language Processing
 
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
 
Deep Learning, Where Are You Going?
Deep Learning, Where Are You Going?Deep Learning, Where Are You Going?
Deep Learning, Where Are You Going?
 
Doktorantūras semināra 3. prezentācija
Doktorantūras semināra 3. prezentācijaDoktorantūras semināra 3. prezentācija
Doktorantūras semināra 3. prezentācija
 
Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot T...
Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot T...Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot T...
Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot T...
 
Benchmarking transfer learning approaches for NLP
Benchmarking transfer learning approaches for NLPBenchmarking transfer learning approaches for NLP
Benchmarking transfer learning approaches for NLP
 
Viva
VivaViva
Viva
 
NLP applicata a LIS
NLP applicata a LISNLP applicata a LIS
NLP applicata a LIS
 
A Combined Method for E-Learning Ontology Population based on NLP and User Ac...
A Combined Method for E-Learning Ontology Population based on NLP and User Ac...A Combined Method for E-Learning Ontology Population based on NLP and User Ac...
A Combined Method for E-Learning Ontology Population based on NLP and User Ac...
 
Natural language processing for requirements engineering: ICSE 2021 Technical...
Natural language processing for requirements engineering: ICSE 2021 Technical...Natural language processing for requirements engineering: ICSE 2021 Technical...
Natural language processing for requirements engineering: ICSE 2021 Technical...
 
Translating phrases in neural machine translation
Translating phrases in neural machine translationTranslating phrases in neural machine translation
Translating phrases in neural machine translation
 
A Proposed PST Model for Enhancing E-Learning Experiences
A Proposed PST Model for Enhancing E-Learning ExperiencesA Proposed PST Model for Enhancing E-Learning Experiences
A Proposed PST Model for Enhancing E-Learning Experiences
 
MULTI-LEARNING SPECIAL SESSION / EDUCON 2018 / EMADRID TEAM
MULTI-LEARNING SPECIAL SESSION / EDUCON 2018 / EMADRID TEAMMULTI-LEARNING SPECIAL SESSION / EDUCON 2018 / EMADRID TEAM
MULTI-LEARNING SPECIAL SESSION / EDUCON 2018 / EMADRID TEAM
 

More from sekizawayuuki

Improving lexical choice in neural machine translation
Improving lexical choice in neural machine translationImproving lexical choice in neural machine translation
Improving lexical choice in neural machine translation
sekizawayuuki
 
Incorporating word reordering knowledge into attention-based neural machine t...
Incorporating word reordering knowledge into attention-based neural machine t...Incorporating word reordering knowledge into attention-based neural machine t...
Incorporating word reordering knowledge into attention-based neural machine t...
sekizawayuuki
 
読解支援@2015 07-13
読解支援@2015 07-13読解支援@2015 07-13
読解支援@2015 07-13
sekizawayuuki
 
読解支援@2015 07-03
読解支援@2015 07-03読解支援@2015 07-03
読解支援@2015 07-03
sekizawayuuki
 
読解支援@2015 06-26
読解支援@2015 06-26読解支援@2015 06-26
読解支援@2015 06-26
sekizawayuuki
 
読解支援@2015 06-12
読解支援@2015 06-12読解支援@2015 06-12
読解支援@2015 06-12
sekizawayuuki
 
読解支援@2015 06-09
読解支援@2015 06-09読解支援@2015 06-09
読解支援@2015 06-09
sekizawayuuki
 
読解支援@2015 06-05
読解支援@2015 06-05読解支援@2015 06-05
読解支援@2015 06-05
sekizawayuuki
 

More from sekizawayuuki (20)

Improving lexical choice in neural machine translation
Improving lexical choice in neural machine translationImproving lexical choice in neural machine translation
Improving lexical choice in neural machine translation
 
Improving Japanese-to-English Neural Machine Translation by Paraphrasing the ...
Improving Japanese-to-English Neural Machine Translation by Paraphrasing the ...Improving Japanese-to-English Neural Machine Translation by Paraphrasing the ...
Improving Japanese-to-English Neural Machine Translation by Paraphrasing the ...
 
Incorporating word reordering knowledge into attention-based neural machine t...
Incorporating word reordering knowledge into attention-based neural machine t...Incorporating word reordering knowledge into attention-based neural machine t...
Incorporating word reordering knowledge into attention-based neural machine t...
 
Coling2016 pre-translation for neural machine translation
Coling2016 pre-translation for neural machine translationColing2016 pre-translation for neural machine translation
Coling2016 pre-translation for neural machine translation
 
Acl読み会@2015 09-18
Acl読み会@2015 09-18Acl読み会@2015 09-18
Acl読み会@2015 09-18
 
読解支援@2015 08-10-6
読解支援@2015 08-10-6読解支援@2015 08-10-6
読解支援@2015 08-10-6
 
読解支援@2015 08-10-5
読解支援@2015 08-10-5読解支援@2015 08-10-5
読解支援@2015 08-10-5
 
読解支援@2015 08-10-4
読解支援@2015 08-10-4読解支援@2015 08-10-4
読解支援@2015 08-10-4
 
読解支援@2015 08-10-3
読解支援@2015 08-10-3読解支援@2015 08-10-3
読解支援@2015 08-10-3
 
読解支援@2015 08-10-2
読解支援@2015 08-10-2読解支援@2015 08-10-2
読解支援@2015 08-10-2
 
読解支援@2015 08-10-1
読解支援@2015 08-10-1読解支援@2015 08-10-1
読解支援@2015 08-10-1
 
読解支援@2015 07-24
読解支援@2015 07-24読解支援@2015 07-24
読解支援@2015 07-24
 
読解支援@2015 07-17
読解支援@2015 07-17読解支援@2015 07-17
読解支援@2015 07-17
 
読解支援@2015 07-13
読解支援@2015 07-13読解支援@2015 07-13
読解支援@2015 07-13
 
読解支援@2015 07-03
読解支援@2015 07-03読解支援@2015 07-03
読解支援@2015 07-03
 
読解支援@2015 06-26
読解支援@2015 06-26読解支援@2015 06-26
読解支援@2015 06-26
 
Naacl読み会@2015 06-24
Naacl読み会@2015 06-24Naacl読み会@2015 06-24
Naacl読み会@2015 06-24
 
読解支援@2015 06-12
読解支援@2015 06-12読解支援@2015 06-12
読解支援@2015 06-12
 
読解支援@2015 06-09
読解支援@2015 06-09読解支援@2015 06-09
読解支援@2015 06-09
 
読解支援@2015 06-05
読解支援@2015 06-05読解支援@2015 06-05
読解支援@2015 06-05
 

Recently uploaded

Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
negromaestrong
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
heathfieldcps1
 
Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
Chris Hunter
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
PECB
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
kauryashika82
 

Recently uploaded (20)

Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptx
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptx
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
 
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...
 
Role Of Transgenic Animal In Target Validation-1.pptx
Role Of Transgenic Animal In Target Validation-1.pptxRole Of Transgenic Animal In Target Validation-1.pptx
Role Of Transgenic Animal In Target Validation-1.pptx
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
 
Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdf
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
 
Unit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxUnit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptx
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan Fellows
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
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
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
Measures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDMeasures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SD
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptx
 

paper introducing: Exploiting source side monolingual data in neural machine translation