SlideShare a Scribd company logo
2017/12/13
EMNLP2017
Translating	Phrases	
in	Neural	Machine	Translation
Xing	Wang,	Zhaopeng Tu,	Deyi Xiong,	Min	Zhang
presentation:	Sekizawa Yuuki
Komachi_lab
Overview
• Phrases	play	an	important	role	in	natural	language	
understanding	and	machine	translation.
• However,	integrating	phrases	into	current	NMT	is	difficult.
• NMT	reads	and	generates	sentences	word	by	word.
• Propose	method
• translate	phrases	in	NMT by	integrating	a	phrase	memory	
storing	target	phrases	from	a	PBSMT system	into	the	
encoder-decoder	architecture	of	NMT.
• Experiment	results	on	the	Chinese	à English	translation	
show	that	the	proposed	model	achieves	significant	
improvements	over	the	baseline	on	various	test	sets.
2017/12/13 1
Previous	works:	Generating	phrases	for	NMT	
• Tang	et	al.	(2016)
• propose	an	external	phrase	memory	that	stores	phrase	
pairs	in	symbolic	forms	for	NMT.
• During	decoding,	the	NMT	decoder	enquires	the	phrase	
memory	and	properly	generates	phrase	translations	
• difference	with	proposed	method
• have	to	prepare	external	phrase	memory	
• cannot	incorporate	structural	information	at	encoder
2
Previous	works:	Combining	NMT	and	SMT	
• Wang	et	al.	(2017)
• integrates	the	SMT	word-level	knowledge	into	NMT
• combine	NMT	posteriors	with	SMT	word	recommendations	
through	linear	interpolation	implemented	by	a	gating	
function	which	dynamically	assigns	the	weights
3
Proposed	method
• incorporates	a	phrase	memory	into	the	
encoder-decoder	architecture	of	NMT	
• generate	the	next	fragment	either	from	a	word	
generation	mode	or	a	phrase	generation	mode	
• word	generation:	generates	a	word	by	the	NMT	decoder	as	
in	the	standard	NMT	framework	
• phrase	generation:	generates	a	multi-word	phrase	by	
enquiring	a	phrase	memory	
• written	by	an	SMT	decoder	based	on	the	dynamic	decoding	
information	from	the	NMT	model	for	each	step	
4
Proposed	method:	Framework
generate	the	next	fragment
balanced	by	a	weight	λ
produced	by	a	neural	
network	based	balancer
5
Proposed	method:	Framework
calculation	of	the
probability	of	generating	y
6
translation:	y =		
words	generated	by	NMT:	w =	
phrases	generated	from	the	phrase	memory	
p =	
The	balancing	weight	λ is	produced	by	the	balancer	– a	multi-layer	network	
fb :	activation	function
Proposed	method:	Well-Formed	Phrases	
• employ	a	source-side	chunker to	chunk	the	source	
sentence,	and	only	phrases	that	corresponds	to	a	source	
chunk	are	used
• We	restrict	ourselves	to	the	well-formed	chunk	phrases	
based	on	the	following	considerations:
1. In	order	to	take	advantage	of	dynamic	programming,	we	
restrict	ourselves	to	non-overlap	phrases.
2. We	explicitly	utilize	the	boundary	information	of	the	source-
side	chunk	phrases,	to	better	guide	the	proposed	model	to	
adopt	a	target	phrase	at	an	appropriate	decoding	step.	
3. We	enable	the	model	to	exploit	the	syntactic	categories	of	
chunk	phrases	to	enhance	the	proposed	model	with	its	
selection	preference	for	special	target	phrases	
7
Proposed	method:	POS	tagging
• we	allow	the	words	in	a	phrase	to	share	the	same	
chunk	tag	and	introduce	a	special	tag	for	the	
beginning	word.	
• e.g.	,	NP “	信息 安全 (information	security)”	
tag	sequence	should	be	“NP_B	NP”	
• The	input	of	NMT:	
8
word
embedding
tag
embedding
Phrase	memory
• The	phrase	memory	stores	relevant	target	phrases	provided	by	an	
SMT	model	trained	on	the	same	bilingual	corpora	
• Writing	to	Phrase	Memory
• pl: target	phrase
• x(pl): corresponding	source	span
• hm(pl ,	x(pl)):	SMT	feature	function
• wm:	SMT	feature	function’s	weight.	
• The	feature	weights	can	be	tuned	by	the	minimum	error	rate	
training	(MERT)	algorithm
9
• When	phrases	are	read	from	the	memory,	they	are	rescored	by	a	
neural	network	based	score	function.
• The	score	function	takes	as	input	the	phrase	itself	and	decoding	
information	from	NMT	(i =	t(pl)	denotes	the	current	decoding	step):	
• g():	either	an	identity	or	a	non-linear	function	
• e():	the	representation	of	phrase	from	RNN
• scores	are	normalized	for	all	phrases	in	the	phrase	memory	
• probability	calculation	is	controlled	with	parameters
• trained	together	with	the	parameters	from	the	NMT	model
Reading	Phrase	Memory	
10
Proposed	method:	Training
• Formally,	we	train	both	the	default	parameters	of	
standard	NMT	and	the	new	parameters	associated	
with	phrase	generation	on	a	set	of	training	examples	
• The	trained	model	is	expected	to	produce	a	higher	
balance	weight	λ and	phrase	probability	P(phrase)
• when	a	phrase	is	selected	from	the	memory,	and	lower	
scores	in	other	cases.	
11
Proposed	method:	Decoding
• NMT	decoder	generates	a	target	sentence
(a	mixture	of	words	and	phrases)	
• we	design	a	variant	of	beam	search	strategy:	
• Due	to	the	different	granularities	of	words	and	phrases,	
• decoding	step	i
1. we	compute	P(phrase)	for	all	phrases	in	the	phrase	memory
P(word)	for	all	words	in	NMT	vocabulary
2. balancer	outputs	a	balancing	weight	λi (λi × P(phrase)	and	(1	−	λi)	× (Pword))
3. the	NMT	decoder	generates	a	proper	phrase	or	word	of	the	highest	probability.	
• If	a	target	phrase	in	the	phrase	memory	has	the	highest	probability,	
the	decoder	generates	the	target	phrase	to	complete	the	multi-
word	phrase	generation	process
• updates	its	decoding	state	by	consuming	the	words	in	the	selected	phrase
• All	translation	hypotheses	are	placed	in	the	corresponding	beams	according	to	the	
number	of	generated	target	words.	 12
Experiments:	MT	settings
• corpus:	Chinese	à English
• train:	1.25M	sentece pairs	(27.9	Ch words	34.5M	En words)
• LDC2002E18,	LDC2003E07,	LDC2003E14,	Hansards	portion	of	
LDC2004T07,	LDC2004T08	and	LDC2005T06	 max	length	=	50
• dev:	NIST06	
• test:	NIST04,	NIST05,	NIST08	
• compared	method
• Moses:	PBSMT
• RNNSearch:	Bahdanau 2015
• vocabulary:	30,000,	other	settings:	default
• evaluation:	case-insensitive	BLEU	score
13
Experiment:	phrase	settings
• used	Chinese	chunker (Zhu	et	al.,	2015)
• 13	chunking	tags	appeared	in	our	chunked	sentences	and	
the	size	of	chunking	tag	embedding	was	set	to	10.
• top	5	translations	were	kept	according	to	
• used	as	phrasal	recommendations	for	each	source	chunk	phrase
• In	the	phrase	memory,	we	only	keep	the	top	7	target	
translations	with	highest	SMT	scores	at	each	decoding	step	
14
Result:	BLEU	score
“†”:	significantly	better	than	RNNSearch (p	<	0.05)	
“‡”:	significantly	better	than	RNNSearch (p	<	0.01)	
15
Result:	number	of	sentences
generated	phrases
• a	large	portion	of	translations	take	the	recommended	
phrases,	and	the	number	increases	when	the	
chunking	tag	feature	is	used	
• the	chunking	tag	feature	benefits	the	proposed	model	
on	its	phrase	generation	
16
Analysis:	Syntactic	Categories	of	Generated	Phrases	
• All:	44.5%	percent	of	them	are	fully	correct	
• the	generated	phrases	can	be	retrieved	in	corresponding	references	as	a	
whole	unit	
• NPs higher accuracy:	47.8%	(38.7%	/	81.0%)
• VPs lower accuracy:	21.2%		(1.7%	/	8.0%)
• most	errors	are	related	to	verb	tense,	which	is	the	drawback	of	SMT	models	
17
NP:	noun	phrase
e.g.,	national	laboratory	
QP:	quantifier	phrases
e.g.,	15	seconds
two	weeks
Analysis:	Syntactic	Categories	of	Generated	Phrases	
• New:	13.2%	of	generated	phrases	are	both	new	and	fully	correct,	
which	contribute	most	to	the	performance	improvement	
• VPs,	QPs	are	not	correct
• the	patterns	can	be	well	learned	by	word-based	NMT	models	
18
NP:	noun	phrase
e.g.,	national	laboratory	
QP:	quantifier	phrases
e.g.,	15	seconds
two	weeks
Number	of	Words	in	Generated	Phrases	
• short	phrases	(<4)
• contribute	most	to	the	new	and	fully	correct	phrases	(12.3%)
• long	phrases	(>=	4)
• most	of	them	are	newly	introduced	(10.6%	out	of	13.1%)	
• only	a	few	portion	of	these	phrases	are	fully	correct
long	phrases	have	higher	chance	to	contain	one	or	two	unmatched	words	
19
Analysis:	Effect	of	Generated	Phrases
on	Translation	Performance	
• To	directly	measure	the	improvement	obtained	by	the	phrase	
generation,	we	replace	the	generated	target	phrases	with	a	
special	symbol	“NULL”	in	test	sets.
• The	overall	results	demonstrate	that	neural	machine	
translation	benefits	from	phrase	translation	
20
-1.32
-2.74
Analysis:	Effect	of	Balancer	λ
21
• setting:	RNNSearch +	memory	+	chunking	tag
n RNNSearch:	32.48
• using	the	fixed	value	for	the	balancing	weight	
decreases	the	translation	performance	sharply.	
• This	demonstrates	that	the	neural	network	based	balancer	
is	an	essential	component	for	the	proposed	model.
Comparison:	related	work
• Our	approach	is	related	to	our	previous	work	(Wang	
et	al.,	2017)	which	integrates	the	SMT	word-level	
knowledge	into	NMT.	(+	word	level	recommendation)
22
Analysis:	translation	examples
• wrong	translation
• 手提电脑à laptop	computers	(correct:	laptop	(ラップトップ)	)
• if	chunked	as	a	phrase	unit
• 广东省à guangdong province	(広東省)
• appeared	in	the	baseline	system	
• Proposed	method	do	not	lead	to	improvements	in	BLEU.	
23
Conclusion
• we	have	presented	a	novel	model	to	translate	source	phrases	
and	generate	target	phrase	translations	in	NMT
• integrating	the	phrase	memory	into	the	encoder-decoder	architecture.	
• At	decoding,	the	SMT	model	dynamically	generates	relevant	target	
phrases	with	contextual	information	provided	by	the	NMT	model	and	
writes	them	to	the	phrase	memory.	
• Then	the	proposed	model	reads	the	phrase	memory	and	uses	the	
balancer	to	make	probability	estimations	for	the	phrases	in	the	phrase	
memory.	
• Finally	the	NMT	decoder	selects	a	phrase	from	the	phrase	memory	or	
a	word	from	the	vocabulary	of	the	highest	probability	to	generate.	
• Experiment	results	on	Chinese	à English	translation	have	
demonstrated	that	the	proposed	model	can	significantly	
improve	the	translation	performance.	
24

More Related Content

What's hot

Bert
BertBert
Interspeech 2017 s_miyoshi
Interspeech 2017 s_miyoshiInterspeech 2017 s_miyoshi
Interspeech 2017 s_miyoshi
Hiroyuki Miyoshi
 
Identification of Fertile Translations in Comparable Corpora: a Morpho-Compos...
Identification of Fertile Translations in Comparable Corpora: a Morpho-Compos...Identification of Fertile Translations in Comparable Corpora: a Morpho-Compos...
Identification of Fertile Translations in Comparable Corpora: a Morpho-Compos...
Estelle Delpech
 
Shallow parser for hindi language with an input from a transliterator
Shallow parser for hindi language with an input from a transliteratorShallow parser for hindi language with an input from a transliterator
Shallow parser for hindi language with an input from a transliterator
Shashank Shisodia
 
[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-...
Hayahide Yamagishi
 
Effect of Machine Translation in Interlingual Conversation: Lessons from a Fo...
Effect of Machine Translation in Interlingual Conversation: Lessons from a Fo...Effect of Machine Translation in Interlingual Conversation: Lessons from a Fo...
Effect of Machine Translation in Interlingual Conversation: Lessons from a Fo...
Kotaro Hara
 
Deep Learning勉強会@小町研 "Learning Character-level Representations for Part-of-Sp...
Deep Learning勉強会@小町研 "Learning Character-level Representations for Part-of-Sp...Deep Learning勉強会@小町研 "Learning Character-level Representations for Part-of-Sp...
Deep Learning勉強会@小町研 "Learning Character-level Representations for Part-of-Sp...
Yuki Tomo
 

What's hot (7)

Bert
BertBert
Bert
 
Interspeech 2017 s_miyoshi
Interspeech 2017 s_miyoshiInterspeech 2017 s_miyoshi
Interspeech 2017 s_miyoshi
 
Identification of Fertile Translations in Comparable Corpora: a Morpho-Compos...
Identification of Fertile Translations in Comparable Corpora: a Morpho-Compos...Identification of Fertile Translations in Comparable Corpora: a Morpho-Compos...
Identification of Fertile Translations in Comparable Corpora: a Morpho-Compos...
 
Shallow parser for hindi language with an input from a transliterator
Shallow parser for hindi language with an input from a transliteratorShallow parser for hindi language with an input from a transliterator
Shallow parser for hindi language with an input from a transliterator
 
[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-...
 
Effect of Machine Translation in Interlingual Conversation: Lessons from a Fo...
Effect of Machine Translation in Interlingual Conversation: Lessons from a Fo...Effect of Machine Translation in Interlingual Conversation: Lessons from a Fo...
Effect of Machine Translation in Interlingual Conversation: Lessons from a Fo...
 
Deep Learning勉強会@小町研 "Learning Character-level Representations for Part-of-Sp...
Deep Learning勉強会@小町研 "Learning Character-level Representations for Part-of-Sp...Deep Learning勉強会@小町研 "Learning Character-level Representations for Part-of-Sp...
Deep Learning勉強会@小町研 "Learning Character-level Representations for Part-of-Sp...
 

Similar to Translating phrases in neural machine translation

End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF
End-to-end sequence labeling via bi-directional LSTM-CNNs-CRFEnd-to-end sequence labeling via bi-directional LSTM-CNNs-CRF
End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF
Jayavardhan Reddy Peddamail
 
IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...
IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...
IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...
IRJET Journal
 
Source side pre-ordering using recurrent neural networks for English-Myanmar ...
Source side pre-ordering using recurrent neural networks for English-Myanmar ...Source side pre-ordering using recurrent neural networks for English-Myanmar ...
Source side pre-ordering using recurrent neural networks for English-Myanmar ...
IJECEIAES
 
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
khyati gupta
 
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
khyati gupta
 
project present
project presentproject present
project present
khyati gupta
 
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
 
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...
Vimukthi Wickramasinghe
 
Machine Translation Introduction
Machine Translation IntroductionMachine Translation Introduction
Machine Translation Introduction
nlab_utokyo
 
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
IRJET Journal
 
Applications of Large Language Models in Materials Discovery and Design
Applications of Large Language Models in Materials Discovery and DesignApplications of Large Language Models in Materials Discovery and Design
Applications of Large Language Models in Materials Discovery and Design
Anubhav Jain
 
Deep network notes.pdf
Deep network notes.pdfDeep network notes.pdf
Deep network notes.pdf
Ramya Nellutla
 
2010 PACLIC - pay attention to categories
2010 PACLIC - pay attention to categories2010 PACLIC - pay attention to categories
2010 PACLIC - pay attention to categories
WarNik Chow
 
Seq2seq Model to Tokenize the Chinese Language
Seq2seq Model to Tokenize the Chinese LanguageSeq2seq Model to Tokenize the Chinese Language
Seq2seq Model to Tokenize the Chinese Language
Jinho Choi
 
MT Use in Lingosail, by Yongpeng Wei, Lingosail
MT Use in Lingosail, by Yongpeng Wei, LingosailMT Use in Lingosail, by Yongpeng Wei, Lingosail
MT Use in Lingosail, by Yongpeng Wei, Lingosail
TAUS - The Language Data Network
 
Nlp research presentation
Nlp research presentationNlp research presentation
Nlp research presentation
Surya Sg
 
Phrase break prediction with bidirectional encoder representations in Japanes...
Phrase break prediction with bidirectional encoder representations in Japanes...Phrase break prediction with bidirectional encoder representations in Japanes...
Phrase break prediction with bidirectional encoder representations in Japanes...
Kosuke Futamata
 
The NLP Muppets revolution!
The NLP Muppets revolution!The NLP Muppets revolution!
The NLP Muppets revolution!
Fabio Petroni, PhD
 
Yves Peirsman - Deep Learning for NLP
Yves Peirsman - Deep Learning for NLPYves Peirsman - Deep Learning for NLP
Yves Peirsman - Deep Learning for NLP
Hendrik D'Oosterlinck
 
Neural machine translation of rare words with subword units
Neural machine translation of rare words with subword unitsNeural machine translation of rare words with subword units
Neural machine translation of rare words with subword units
Tae Hwan Jung
 

Similar to Translating phrases in neural machine translation (20)

End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF
End-to-end sequence labeling via bi-directional LSTM-CNNs-CRFEnd-to-end sequence labeling via bi-directional LSTM-CNNs-CRF
End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF
 
IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...
IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...
IRJET- Survey on Deep Learning Approaches for Phrase Structure Identification...
 
Source side pre-ordering using recurrent neural networks for English-Myanmar ...
Source side pre-ordering using recurrent neural networks for English-Myanmar ...Source side pre-ordering using recurrent neural networks for English-Myanmar ...
Source side pre-ordering using recurrent neural networks for English-Myanmar ...
 
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
 
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
 
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
 
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machi...
 
Machine Translation Introduction
Machine Translation IntroductionMachine Translation Introduction
Machine Translation Introduction
 
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
 
Applications of Large Language Models in Materials Discovery and Design
Applications of Large Language Models in Materials Discovery and DesignApplications of Large Language Models in Materials Discovery and Design
Applications of Large Language Models in Materials Discovery and Design
 
Deep network notes.pdf
Deep network notes.pdfDeep network notes.pdf
Deep network notes.pdf
 
2010 PACLIC - pay attention to categories
2010 PACLIC - pay attention to categories2010 PACLIC - pay attention to categories
2010 PACLIC - pay attention to categories
 
Seq2seq Model to Tokenize the Chinese Language
Seq2seq Model to Tokenize the Chinese LanguageSeq2seq Model to Tokenize the Chinese Language
Seq2seq Model to Tokenize the Chinese Language
 
MT Use in Lingosail, by Yongpeng Wei, Lingosail
MT Use in Lingosail, by Yongpeng Wei, LingosailMT Use in Lingosail, by Yongpeng Wei, Lingosail
MT Use in Lingosail, by Yongpeng Wei, Lingosail
 
Nlp research presentation
Nlp research presentationNlp research presentation
Nlp research presentation
 
Phrase break prediction with bidirectional encoder representations in Japanes...
Phrase break prediction with bidirectional encoder representations in Japanes...Phrase break prediction with bidirectional encoder representations in Japanes...
Phrase break prediction with bidirectional encoder representations in Japanes...
 
The NLP Muppets revolution!
The NLP Muppets revolution!The NLP Muppets revolution!
The NLP Muppets revolution!
 
Yves Peirsman - Deep Learning for NLP
Yves Peirsman - Deep Learning for NLPYves Peirsman - Deep Learning for NLP
Yves Peirsman - Deep Learning for NLP
 
Neural machine translation of rare words with subword units
Neural machine translation of rare words with subword unitsNeural machine translation of rare words with subword units
Neural machine translation of rare words with subword units
 

More from sekizawayuuki

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 ...
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
 
paper introducing: Exploiting source side monolingual data in neural machine ...
paper introducing: Exploiting source side monolingual data in neural machine ...paper introducing: Exploiting source side monolingual data in neural machine ...
paper introducing: Exploiting source side monolingual data in neural machine ...
sekizawayuuki
 
目的言語の低頻度語の高頻度語への言い換えによるニューラル機械翻訳の改善
目的言語の低頻度語の高頻度語への言い換えによるニューラル機械翻訳の改善目的言語の低頻度語の高頻度語への言い換えによるニューラル機械翻訳の改善
目的言語の低頻度語の高頻度語への言い換えによるニューラル機械翻訳の改善
sekizawayuuki
 
Emnlp読み会@2017 02-15
Emnlp読み会@2017 02-15Emnlp読み会@2017 02-15
Emnlp読み会@2017 02-15
sekizawayuuki
 
Acl reading@2016 10-26
Acl reading@2016 10-26Acl reading@2016 10-26
Acl reading@2016 10-26
sekizawayuuki
 
[論文紹介]Selecting syntactic, non redundant segments in active learning for mach...
[論文紹介]Selecting syntactic, non redundant segments in active learning for mach...[論文紹介]Selecting syntactic, non redundant segments in active learning for mach...
[論文紹介]Selecting syntactic, non redundant segments in active learning for mach...
sekizawayuuki
 
Nlp2016 sekizawa
Nlp2016 sekizawaNlp2016 sekizawa
Nlp2016 sekizawa
sekizawayuuki
 
Emnlp読み会@2015 10-09
Emnlp読み会@2015 10-09Emnlp読み会@2015 10-09
Emnlp読み会@2015 10-09
sekizawayuuki
 
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
sekizawayuuki
 
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
sekizawayuuki
 
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
sekizawayuuki
 
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
sekizawayuuki
 
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
sekizawayuuki
 
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
sekizawayuuki
 
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
sekizawayuuki
 
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
sekizawayuuki
 
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
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 07-03sekizawayuuki
 

More from sekizawayuuki (20)

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...
 
paper introducing: Exploiting source side monolingual data in neural machine ...
paper introducing: Exploiting source side monolingual data in neural machine ...paper introducing: Exploiting source side monolingual data in neural machine ...
paper introducing: Exploiting source side monolingual data in neural machine ...
 
目的言語の低頻度語の高頻度語への言い換えによるニューラル機械翻訳の改善
目的言語の低頻度語の高頻度語への言い換えによるニューラル機械翻訳の改善目的言語の低頻度語の高頻度語への言い換えによるニューラル機械翻訳の改善
目的言語の低頻度語の高頻度語への言い換えによるニューラル機械翻訳の改善
 
Emnlp読み会@2017 02-15
Emnlp読み会@2017 02-15Emnlp読み会@2017 02-15
Emnlp読み会@2017 02-15
 
Acl reading@2016 10-26
Acl reading@2016 10-26Acl reading@2016 10-26
Acl reading@2016 10-26
 
[論文紹介]Selecting syntactic, non redundant segments in active learning for mach...
[論文紹介]Selecting syntactic, non redundant segments in active learning for mach...[論文紹介]Selecting syntactic, non redundant segments in active learning for mach...
[論文紹介]Selecting syntactic, non redundant segments in active learning for mach...
 
Nlp2016 sekizawa
Nlp2016 sekizawaNlp2016 sekizawa
Nlp2016 sekizawa
 
Emnlp読み会@2015 10-09
Emnlp読み会@2015 10-09Emnlp読み会@2015 10-09
Emnlp読み会@2015 10-09
 
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
 

Recently uploaded

RESULTS OF THE EVALUATION QUESTIONNAIRE.pptx
RESULTS OF THE EVALUATION QUESTIONNAIRE.pptxRESULTS OF THE EVALUATION QUESTIONNAIRE.pptx
RESULTS OF THE EVALUATION QUESTIONNAIRE.pptx
zuzanka
 
RHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem students
RHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem studentsRHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem students
RHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem students
Himanshu Rai
 
Level 3 NCEA - NZ: A Nation In the Making 1872 - 1900 SML.ppt
Level 3 NCEA - NZ: A  Nation In the Making 1872 - 1900 SML.pptLevel 3 NCEA - NZ: A  Nation In the Making 1872 - 1900 SML.ppt
Level 3 NCEA - NZ: A Nation In the Making 1872 - 1900 SML.ppt
Henry Hollis
 
BÀI TẬP BỔ TRỢ TIẾNG ANH LỚP 9 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2024-2025 - ...
BÀI TẬP BỔ TRỢ TIẾNG ANH LỚP 9 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2024-2025 - ...BÀI TẬP BỔ TRỢ TIẾNG ANH LỚP 9 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2024-2025 - ...
BÀI TẬP BỔ TRỢ TIẾNG ANH LỚP 9 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2024-2025 - ...
Nguyen Thanh Tu Collection
 
Skimbleshanks-The-Railway-Cat by T S Eliot
Skimbleshanks-The-Railway-Cat by T S EliotSkimbleshanks-The-Railway-Cat by T S Eliot
Skimbleshanks-The-Railway-Cat by T S Eliot
nitinpv4ai
 
Pharmaceutics Pharmaceuticals best of brub
Pharmaceutics Pharmaceuticals best of brubPharmaceutics Pharmaceuticals best of brub
Pharmaceutics Pharmaceuticals best of brub
danielkiash986
 
skeleton System.pdf (skeleton system wow)
skeleton System.pdf (skeleton system wow)skeleton System.pdf (skeleton system wow)
skeleton System.pdf (skeleton system wow)
Mohammad Al-Dhahabi
 
BÀI TẬP DẠY THÊM TIẾNG ANH LỚP 7 CẢ NĂM FRIENDS PLUS SÁCH CHÂN TRỜI SÁNG TẠO ...
BÀI TẬP DẠY THÊM TIẾNG ANH LỚP 7 CẢ NĂM FRIENDS PLUS SÁCH CHÂN TRỜI SÁNG TẠO ...BÀI TẬP DẠY THÊM TIẾNG ANH LỚP 7 CẢ NĂM FRIENDS PLUS SÁCH CHÂN TRỜI SÁNG TẠO ...
BÀI TẬP DẠY THÊM TIẾNG ANH LỚP 7 CẢ NĂM FRIENDS PLUS SÁCH CHÂN TRỜI SÁNG TẠO ...
Nguyen Thanh Tu Collection
 
Elevate Your Nonprofit's Online Presence_ A Guide to Effective SEO Strategies...
Elevate Your Nonprofit's Online Presence_ A Guide to Effective SEO Strategies...Elevate Your Nonprofit's Online Presence_ A Guide to Effective SEO Strategies...
Elevate Your Nonprofit's Online Presence_ A Guide to Effective SEO Strategies...
TechSoup
 
CIS 4200-02 Group 1 Final Project Report (1).pdf
CIS 4200-02 Group 1 Final Project Report (1).pdfCIS 4200-02 Group 1 Final Project Report (1).pdf
CIS 4200-02 Group 1 Final Project Report (1).pdf
blueshagoo1
 
Benner "Expanding Pathways to Publishing Careers"
Benner "Expanding Pathways to Publishing Careers"Benner "Expanding Pathways to Publishing Careers"
Benner "Expanding Pathways to Publishing Careers"
National Information Standards Organization (NISO)
 
Présentationvvvvvvvvvvvvvvvvvvvvvvvvvvvv2.pptx
Présentationvvvvvvvvvvvvvvvvvvvvvvvvvvvv2.pptxPrésentationvvvvvvvvvvvvvvvvvvvvvvvvvvvv2.pptx
Présentationvvvvvvvvvvvvvvvvvvvvvvvvvvvv2.pptx
siemaillard
 
Stack Memory Organization of 8086 Microprocessor
Stack Memory Organization of 8086 MicroprocessorStack Memory Organization of 8086 Microprocessor
Stack Memory Organization of 8086 Microprocessor
JomonJoseph58
 
REASIGNACION 2024 UGEL CHUPACA 2024 UGEL CHUPACA.pdf
REASIGNACION 2024 UGEL CHUPACA 2024 UGEL CHUPACA.pdfREASIGNACION 2024 UGEL CHUPACA 2024 UGEL CHUPACA.pdf
REASIGNACION 2024 UGEL CHUPACA 2024 UGEL CHUPACA.pdf
giancarloi8888
 
THE SACRIFICE HOW PRO-PALESTINE PROTESTS STUDENTS ARE SACRIFICING TO CHANGE T...
THE SACRIFICE HOW PRO-PALESTINE PROTESTS STUDENTS ARE SACRIFICING TO CHANGE T...THE SACRIFICE HOW PRO-PALESTINE PROTESTS STUDENTS ARE SACRIFICING TO CHANGE T...
THE SACRIFICE HOW PRO-PALESTINE PROTESTS STUDENTS ARE SACRIFICING TO CHANGE T...
indexPub
 
مصحف القراءات العشر أعد أحرف الخلاف سمير بسيوني.pdf
مصحف القراءات العشر   أعد أحرف الخلاف سمير بسيوني.pdfمصحف القراءات العشر   أعد أحرف الخلاف سمير بسيوني.pdf
مصحف القراءات العشر أعد أحرف الخلاف سمير بسيوني.pdf
سمير بسيوني
 
Chapter wise All Notes of First year Basic Civil Engineering.pptx
Chapter wise All Notes of First year Basic Civil Engineering.pptxChapter wise All Notes of First year Basic Civil Engineering.pptx
Chapter wise All Notes of First year Basic Civil Engineering.pptx
Denish Jangid
 
Andreas Schleicher presents PISA 2022 Volume III - Creative Thinking - 18 Jun...
Andreas Schleicher presents PISA 2022 Volume III - Creative Thinking - 18 Jun...Andreas Schleicher presents PISA 2022 Volume III - Creative Thinking - 18 Jun...
Andreas Schleicher presents PISA 2022 Volume III - Creative Thinking - 18 Jun...
EduSkills OECD
 
Juneteenth Freedom Day 2024 David Douglas School District
Juneteenth Freedom Day 2024 David Douglas School DistrictJuneteenth Freedom Day 2024 David Douglas School District
Juneteenth Freedom Day 2024 David Douglas School District
David Douglas School District
 
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptx
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptxBeyond Degrees - Empowering the Workforce in the Context of Skills-First.pptx
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptx
EduSkills OECD
 

Recently uploaded (20)

RESULTS OF THE EVALUATION QUESTIONNAIRE.pptx
RESULTS OF THE EVALUATION QUESTIONNAIRE.pptxRESULTS OF THE EVALUATION QUESTIONNAIRE.pptx
RESULTS OF THE EVALUATION QUESTIONNAIRE.pptx
 
RHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem students
RHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem studentsRHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem students
RHEOLOGY Physical pharmaceutics-II notes for B.pharm 4th sem students
 
Level 3 NCEA - NZ: A Nation In the Making 1872 - 1900 SML.ppt
Level 3 NCEA - NZ: A  Nation In the Making 1872 - 1900 SML.pptLevel 3 NCEA - NZ: A  Nation In the Making 1872 - 1900 SML.ppt
Level 3 NCEA - NZ: A Nation In the Making 1872 - 1900 SML.ppt
 
BÀI TẬP BỔ TRỢ TIẾNG ANH LỚP 9 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2024-2025 - ...
BÀI TẬP BỔ TRỢ TIẾNG ANH LỚP 9 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2024-2025 - ...BÀI TẬP BỔ TRỢ TIẾNG ANH LỚP 9 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2024-2025 - ...
BÀI TẬP BỔ TRỢ TIẾNG ANH LỚP 9 CẢ NĂM - GLOBAL SUCCESS - NĂM HỌC 2024-2025 - ...
 
Skimbleshanks-The-Railway-Cat by T S Eliot
Skimbleshanks-The-Railway-Cat by T S EliotSkimbleshanks-The-Railway-Cat by T S Eliot
Skimbleshanks-The-Railway-Cat by T S Eliot
 
Pharmaceutics Pharmaceuticals best of brub
Pharmaceutics Pharmaceuticals best of brubPharmaceutics Pharmaceuticals best of brub
Pharmaceutics Pharmaceuticals best of brub
 
skeleton System.pdf (skeleton system wow)
skeleton System.pdf (skeleton system wow)skeleton System.pdf (skeleton system wow)
skeleton System.pdf (skeleton system wow)
 
BÀI TẬP DẠY THÊM TIẾNG ANH LỚP 7 CẢ NĂM FRIENDS PLUS SÁCH CHÂN TRỜI SÁNG TẠO ...
BÀI TẬP DẠY THÊM TIẾNG ANH LỚP 7 CẢ NĂM FRIENDS PLUS SÁCH CHÂN TRỜI SÁNG TẠO ...BÀI TẬP DẠY THÊM TIẾNG ANH LỚP 7 CẢ NĂM FRIENDS PLUS SÁCH CHÂN TRỜI SÁNG TẠO ...
BÀI TẬP DẠY THÊM TIẾNG ANH LỚP 7 CẢ NĂM FRIENDS PLUS SÁCH CHÂN TRỜI SÁNG TẠO ...
 
Elevate Your Nonprofit's Online Presence_ A Guide to Effective SEO Strategies...
Elevate Your Nonprofit's Online Presence_ A Guide to Effective SEO Strategies...Elevate Your Nonprofit's Online Presence_ A Guide to Effective SEO Strategies...
Elevate Your Nonprofit's Online Presence_ A Guide to Effective SEO Strategies...
 
CIS 4200-02 Group 1 Final Project Report (1).pdf
CIS 4200-02 Group 1 Final Project Report (1).pdfCIS 4200-02 Group 1 Final Project Report (1).pdf
CIS 4200-02 Group 1 Final Project Report (1).pdf
 
Benner "Expanding Pathways to Publishing Careers"
Benner "Expanding Pathways to Publishing Careers"Benner "Expanding Pathways to Publishing Careers"
Benner "Expanding Pathways to Publishing Careers"
 
Présentationvvvvvvvvvvvvvvvvvvvvvvvvvvvv2.pptx
Présentationvvvvvvvvvvvvvvvvvvvvvvvvvvvv2.pptxPrésentationvvvvvvvvvvvvvvvvvvvvvvvvvvvv2.pptx
Présentationvvvvvvvvvvvvvvvvvvvvvvvvvvvv2.pptx
 
Stack Memory Organization of 8086 Microprocessor
Stack Memory Organization of 8086 MicroprocessorStack Memory Organization of 8086 Microprocessor
Stack Memory Organization of 8086 Microprocessor
 
REASIGNACION 2024 UGEL CHUPACA 2024 UGEL CHUPACA.pdf
REASIGNACION 2024 UGEL CHUPACA 2024 UGEL CHUPACA.pdfREASIGNACION 2024 UGEL CHUPACA 2024 UGEL CHUPACA.pdf
REASIGNACION 2024 UGEL CHUPACA 2024 UGEL CHUPACA.pdf
 
THE SACRIFICE HOW PRO-PALESTINE PROTESTS STUDENTS ARE SACRIFICING TO CHANGE T...
THE SACRIFICE HOW PRO-PALESTINE PROTESTS STUDENTS ARE SACRIFICING TO CHANGE T...THE SACRIFICE HOW PRO-PALESTINE PROTESTS STUDENTS ARE SACRIFICING TO CHANGE T...
THE SACRIFICE HOW PRO-PALESTINE PROTESTS STUDENTS ARE SACRIFICING TO CHANGE T...
 
مصحف القراءات العشر أعد أحرف الخلاف سمير بسيوني.pdf
مصحف القراءات العشر   أعد أحرف الخلاف سمير بسيوني.pdfمصحف القراءات العشر   أعد أحرف الخلاف سمير بسيوني.pdf
مصحف القراءات العشر أعد أحرف الخلاف سمير بسيوني.pdf
 
Chapter wise All Notes of First year Basic Civil Engineering.pptx
Chapter wise All Notes of First year Basic Civil Engineering.pptxChapter wise All Notes of First year Basic Civil Engineering.pptx
Chapter wise All Notes of First year Basic Civil Engineering.pptx
 
Andreas Schleicher presents PISA 2022 Volume III - Creative Thinking - 18 Jun...
Andreas Schleicher presents PISA 2022 Volume III - Creative Thinking - 18 Jun...Andreas Schleicher presents PISA 2022 Volume III - Creative Thinking - 18 Jun...
Andreas Schleicher presents PISA 2022 Volume III - Creative Thinking - 18 Jun...
 
Juneteenth Freedom Day 2024 David Douglas School District
Juneteenth Freedom Day 2024 David Douglas School DistrictJuneteenth Freedom Day 2024 David Douglas School District
Juneteenth Freedom Day 2024 David Douglas School District
 
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptx
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptxBeyond Degrees - Empowering the Workforce in the Context of Skills-First.pptx
Beyond Degrees - Empowering the Workforce in the Context of Skills-First.pptx
 

Translating phrases in neural machine translation