Deciphering Foreign Language
|
|
|
- Curtis Fields
- 10 years ago
- Views:
Transcription
1 Deciphering Foreign Language NLP 1! Sujith Ravi and Kevin Knight Information Sciences Institute University of Southern California! 2
2 Statistical Machine Translation (MT) Current MT systems Bilingual text (Spanish) Garcia y asociados (English) Garcia and associates (Spanish) sus grupos están en Europa (English) its groups are in Europe TRAIN Translation tables associates/ asociados 0.8 groups/ grupos 0.9 2
3 Statistical Machine Translation (MT) Current MT systems Bilingual text Spanish/English (Spanish) Garcia y asociados (English) Garcia and associates (Spanish) sus grupos están en Europa (English) its groups are in Europe TRAIN Translation tables associates/ asociados 0.8 groups/ grupos 0.9 2
4 Statistical Machine Translation (MT) Current MT systems Bilingual text Spanish/English (Spanish) Garcia y asociados (English) Garcia and associates Japanese/German (Spanish) sus grupos están en Europa (English) its groups are in Europe TRAIN Translation tables associates/ asociados 0.8 groups/ grupos 0.9 2
5 Statistical Machine Translation (MT) Current MT systems Bilingual text Spanish/English (Spanish) Garcia y asociados (English) Garcia and associates Japanese/German (Spanish) sus grupos están en Europa (English) Malayalam/English its groups are in Europe TRAIN Translation tables associates/ asociados 0.8 groups/ grupos 0.9 2
6 Statistical Machine Translation (MT) Current MT systems Bilingual text Spanish/English (Spanish) Garcia y asociados (English) Garcia and associates Japanese/German (Spanish) sus grupos están en Europa (English) Malayalam/English its groups are in Europe Swahili/German TRAIN Translation tables associates/ asociados 0.8 groups/ grupos 0.9 2
7 Statistical Machine Translation (MT) Current MT systems Bilingual text Spanish/English (Spanish) Garcia y asociados (English) Garcia and associates Japanese/German (Spanish) sus grupos están en Europa (English) Malayalam/English its groups are in Europe Swahili/German BOTTLENECK TRAIN Translation tables associates/ asociados 0.8 groups/ grupos 0.9 2
8 Statistical Machine Translation (MT) Current MT systems Can we get rid of parallel data? Bilingual text Spanish/English (Spanish) Garcia y asociados (English) Garcia and associates Japanese/German (Spanish) sus grupos están en Europa (English) Malayalam/English its groups are in Europe Swahili/German BOTTLENECK TRAIN Translation tables associates/ asociados 0.8 groups/ grupos 0.9 2
9 Statistical Machine Translation (MT) Current MT systems Can we get rid of parallel data? Bilingual text Spanish/English (Spanish) Garcia y asociados (English) Garcia and associates Japanese/German (Spanish) sus grupos están en Europa (English) Malayalam/English its groups are in Europe Swahili/German BOTTLENECK TRAIN Translation tables associates/ asociados 0.8 groups/ grupos 0.9 Monolingual corpora Spanish text English text TRAIN Translation tables associates/ asociados 0.8 2
10 Statistical Machine Translation (MT) Current MT systems Can we get rid of parallel data? Bilingual text Spanish/English (Spanish) Garcia y asociados (English) Garcia and associates Japanese/German (Spanish) sus grupos están en Europa (English) Malayalam/English its groups are in Europe Swahili/German BOTTLENECK TRAIN Translation tables associates/ asociados 0.8 groups/ grupos 0.9 PLENTY PLENTY Monolingual corpora Spanish text English text TRAIN Translation tables associates/ asociados 0.8 2
11 Machine Translation without parallel data Getting Rid of Parallel Data MT system trained on non-parallel data useful for rare language-pairs (limited/no parallel data) 3
12 Machine Translation without parallel data Getting Rid of Parallel Data MT system trained on non-parallel data useful for rare language-pairs (limited/no parallel data) Monolingual corpora Spanish text English text TRAIN Translation tables associates/ asociados 0.8 3
13 Machine Translation without parallel data Getting Rid of Parallel Data MT system trained on non-parallel data useful for rare language-pairs (limited/no parallel data) Monolingual corpora Spanish text English text TRAIN Translation tables associates/ asociados 0.8 Goal not to beat existing MT systems, instead Can we build a reasonably good MT system from scratch without any parallel data? monolingual resources available in plenty 3
14 Related Work Machine Translation without parallel data Extracting bilingual lexical connections from comparable corpora exploit word context frequencies (Fung, 1995; Rapp, 1995; Koehn & Knight, 2001) Canonical Correlation Analysis (CCA) method (Haghighi & Klein, 2008) Mining parallel sentence pairs for MT training using comparable corpora (Munteanu et al., 2004) need dictionary, some initial parallel data 4
15 NLP Our Contributions New MT system built from scratch without parallel data novel decipherment approach for translation novel methods for training translation models from non-parallel text Bayesian training for IBM 3 translation model Novel methods to deal with large-scale vocabularies inherent in MT problems Empirical studies for MT decipherment 5
16 Rest of this Talk Introduction Related Work New Idea for Language Translation Step 1 Word Substitution Step 2 Foreign Language as a Cipher Conclusion 6
17 New Cracking the MT Code When I look at an article in Spanish, I say to myself, this is really English, but it has been encoded in some strange symbols. Now I will proceed to decode Warren Weaver (1947) (Spanish) Ciphertext este es un sistema de cifrado complejo 7
18 New Cracking the MT Code When I look at an article in Spanish, I say to myself, this is really English, but it has been encoded in some strange symbols. Now I will proceed to decode Warren Weaver (1947) (Spanish) Ciphertext este es un sistema de cifrado complejo (English) Plaintext this is a complex cipher 7
19 New MT Decipherment without Parallel Data f Spanish corpus El portal web permite la búsqueda por todo tipo de métodos. Por un lado, Wikileaks ha ordenado la documentación por diferentes categorías atendiendo a los hechos más notables. Desde el tipo de suceso (evento criminal, fuego amigo,
20 New MT Decipherment without Parallel Data P(e) e English? P(f e) f Spanish corpus English Language Model English-to-Spanish Translation Model key El portal web permite la búsqueda por todo tipo de métodos. Por un lado, Wikileaks ha ordenado la documentación por diferentes categorías atendiendo a los hechos más notables. Desde el tipo de suceso (evento criminal, fuego amigo,
21 New MT Decipherment without Parallel Data English corpus (CNN) WikiLeaks website publishes classified military documents from Iraq. The whistle-blower website WikiLeaks published nearly 400,000 classified military documents from the Iraq war on Friday, calling it the largest classified military leak in history,. Language Model Training P(e) e English? P(f e) f Spanish corpus English Language Model English-to-Spanish Translation Model key El portal web permite la búsqueda por todo tipo de métodos. Por un lado, Wikileaks ha ordenado la documentación por diferentes categorías atendiendo a los hechos más notables. Desde el tipo de suceso (evento criminal, fuego amigo,
22 New MT Decipherment without Parallel Data English corpus (CNN) WikiLeaks website publishes classified military documents from Iraq. The whistle-blower website WikiLeaks published nearly 400,000 classified military documents from the Iraq war on Friday, calling it the largest classified military leak in history,. Language Model Training For each f alignments = hidden e translation = hidden P(e) e English? P(f e) f Spanish corpus English Language Model English-to-Spanish Translation Model key El portal web permite la búsqueda por todo tipo de métodos. Por un lado, Wikileaks ha ordenado la documentación por diferentes categorías atendiendo a los hechos más notables. Desde el tipo de suceso (evento criminal, fuego amigo,
23 New MT Decipherment without Parallel Data English corpus (CNN) WikiLeaks website publishes classified military documents from Iraq. The whistle-blower website WikiLeaks published nearly 400,000 classified military documents from the Iraq war on Friday, calling it the largest classified military leak in history,. Language Model Training Train parameters θ to maximize probability of observed foreign text f argmax θ Pθ (f ) argmax θ e Pθ (e, f) argmax θ e P(e). Pθ (f e) TRAINING For each f alignments = hidden e translation = hidden P(e) e English? P(f e) f Spanish corpus English Language Model English-to-Spanish Translation Model key El portal web permite la búsqueda por todo tipo de métodos. Por un lado, Wikileaks ha ordenado la documentación por diferentes categorías atendiendo a los hechos más notables. Desde el tipo de suceso (evento criminal, fuego amigo,
24 Characteristics of Decipherment Key for MT MT Determinism in Key? Linguistic unit of substitution Transposition (re-ordering) Insertion Deletion Scale (vocabulary & data sizes) 9
25 Characteristics of Decipherment Key for MT MT Hard problem! Determinism in Key? Linguistic unit of substitution Transposition (re-ordering) many-to-many Word / Phrase Insertion Deletion Scale (vocabulary & data sizes) Large (100-1M word types) 10
26 Characteristics of Decipherment Key Tackle a simpler problem first! Word Substitution MT Hard problem! Determinism in Key? Linguistic unit of substitution Transposition (re-ordering) Insertion 1-to-1 Word many-to-many Word / Phrase Deletion Scale (vocabulary & data sizes) Large (100-1M word types) 11 Large (100-1M word types)
27 Rest of this Talk Introduction Related Work New Idea for Language Translation Word Substitution Foreign Language as a Cipher Conclusion 12
28 Word Substitution Word Substitution (on the road to MT)!"#$%&'()%$"*)%)#+%*,%-,./*)"0% English words masked by cipher symbols *2(%3,)34(56*)(&%789%$#..*,.%(;<(4$%$"(5(%#5(%"3,&5(&)%'=% 13
29 Word Substitution Word Substitution (on the road to MT)!"#$%&'()%$"*)%)#+%*,%-,./*)"0% !"#$% Learn substitution mappings between English words and cipher symbols !"#$%&'( 1*2(%3,)34(56*)(&%789%$#..*,.%(;<(4$%$"(5(%#5(%"3,&5(&)%'=% 14
30 Word Substitution Word Substitution Decipherment!"#$%&'%(') *)
31 Word Substitution Word Substitution Decipherment!"&'$ &$ ()*+,-.$?!"#$%$&'$!"#$%&'%(') *) /0&12$
32 Word Substitution Word Substitution Decipherment!"&'$ &$ ()*+,-.$?!"#$%$&'$!"#$%&'%(') *) English Language Model 15 /0&12$ Substitution Table
33 Word Substitution Word Substitution Decipherment English corpus LM Training!"&'$ &$ ()*+,-.$?!"#$%$&'$!"#$%&'%(') *) English Language Model 15 /0&12$ Substitution Table
34 Word Substitution Word Substitution Decipherment!"&'$ &$ ()*+,-.$?!"#$%&'%(')!"#$%$&'$ /0&12$ *) 16
35 Word Substitution Word Substitution Decipherment!"&'$ &$ ()*+,-.$?!"#$%&'%(')!"#$%$&'$ *) /0&12$ key contains millions of parameters!!! 16
36 Word Substitution Word Substitution Decipherment!"&'$ &$ ()*+,-.$?!"#$%&'%(')!"#$%$&'$ /0&12$ *) key contains millions of parameters!!! New New 1. EM Decipherment 2. Bayesian Decipherment - EM using new iterative training procedure - Bayesian inference (efficient, parallelized sampling) 16
37 Word Substitution New Word Substitution (1) EM!!"#$%&'(#)*%+#!,-*.)/###! &))0#(1#%(12)#3#4-0*()#567#-*2*7)()2%#! 8$7)/###! Iterative EM! Decoding Viterbi decoding using trained channel (details in paper) 17
38 Word Substitution New Word Substitution (2) Bayesian Several advantages over EM efficient inference, even with higher-order LMs incremental scoring of derivations during sampling novel sample-selection strategy permits fast training no memory bottleneck sparse priors help learn skewed distributions 18
39 Word Substitution Word Substitution (2) Bayesian (continued) Same generative story as EM, replace models with Chinese Restaurant Process (CRP) formulations Base distributions (P0) source = English LM probabilities, channel = uniform Priors source (α) = 10 4, channel (β) = 0.01 Inference via point-wise Gibbs sampling Smart sample-choice selection 19
40 Word Substitution Smart Sample-Choice Selection for Bayesian Decipherment cipher current three eight living here? resample three the living here? resample three a living here?! resample three and living here?! resample three boys living here? resample three gun living here? resample three brick living here? resample three ran living here?!"#$%&'()*+,)-("#$!$%&'()*+,-.!/0,'!1,*0%$!/#2%-3! 40#5'(-6'!#$!),++,#-'!#"!1,*0%$!/#2%-'!*%$!%*#107! 85$$%-/!'#+59#-!!'()*+%!+./'(0+1(233(*+(,-/%;/!10#,1%'! <=,-%!1#)*5/(9#-!!>,?%-!@!(-6!AB!C0(/!($%!/#*&DEE!F!$(-2%6!GH!IJ@!F!AKL!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!M"!@!(-6!A!-%?%$!1#s$$%6B!/0%-!*,12!DEE!$(-6#)!C#$6'7! 20
41 Word Substitution Word Substitution (2) Bayesian (continued) Same generative story as EM, replace models with Chinese Restaurant Process (CRP) formulations Base distributions (P0) source = English LM probabilities, channel = uniform Priors source (α) = 10 4, channel (β) = 0.01 Inference via point-wise Gibbs sampling Smart sample-choice selection Parallelized sampling using Map Reduce (3 to 5-fold faster) Decoding Extract trained channel from final sample, Viterbi-decode (details in paper) 21
42 Word Substitution Word Substitution Results 22
43 Word Substitution Sample Decipherments Cipher Original English Deciphered 23
44 Rest of this Talk Introduction Related Work New Idea for Language Translation Word Substitution Foreign Language as a Cipher Conclusion 24
45 Machine Translation without parallel data Foreign Language as a Cipher!"#$%&'()$*)( +( Spanish corpus 25
46 Machine Translation without parallel data Foreign Language as a Cipher!"&'$ &$ ()*+,-.$?!"#$%$&'$!"#$%&'()$*)( +( /0&12$ Spanish corpus 25
47 Machine Translation without parallel data Foreign Language as a Cipher!"&'$ &$ ()*+,-.$?!"#$%$&'$!"#$%&'()$*)( +( /0&12$ English Language Model English-to-Foreign Translation Model Spanish corpus 25
48 Machine Translation without parallel data Foreign Language as a Cipher English corpus LM Training!"&'$ &$ ()*+,-.$?!"#$%$&'$!"#$%&'()$*)( +( /0&12$ English Language Model English-to-Foreign Translation Model Spanish corpus 25
49 Machine Translation without parallel data Foreign Language as a Cipher Machine Translation without parallel data = Word Substitution English corpus LM Training + transposition + insertion + deletion +!"&'$ &$ ()*+,-.$?!"#$%$&'$!"#$%&'()$*)( +( /0&12$ English Language Model English-to-Foreign Translation Model Spanish corpus 25
50 Machine Translation without parallel data Deciphering Foreign Language!"&'$ &$ ()*+,-.$?!"#$%$&'$ /0&12$ P(f e) can be any translation model used in MT but without parallel data, training is intractable!"#$%&'()$*)( +( (e.g., IBM Model 3) 26
51 Machine Translation without parallel data Deciphering Foreign Language!"&'$ &$ ()*+,-.$?!"#$%$&'$ /0&12$ P(f e) can be any translation model used in MT but without parallel data, training is intractable!"#$%&'()$*)( +( (e.g., IBM Model 3) New New 1. EM Decipherment 2. Bayesian Decipherment - Simple generative story - model can be trained efficiently using EM - IBM Model 3 generative story - Bayesian inference (efficient, parallelized sampling) 26
52 New MT Decipherment (1) EM Machine Translation without parallel data Simple generative story (avoid large-sized fertility, distortion tables) word substitutions insertions deletions local re-ordering Model can be trained efficiently using EM Use prior linguistic knowledge for decipherment morphology, linguistic constraints (e.g., 8 in English maps to 8 in Spanish) Whole-segment language models instead of word n-gram LMs e.g., ARE YOU TALKING ABOUT ME? THANK YOU TALKING ABOUT? 27
53 New Machine Translation without parallel data MT Decipherment (2) Bayesian Generative story IBM Model 3 (popular) translation (word substitution) fertility distortion (transposition) 28
54 New Machine Translation without parallel data MT Decipherment (2) Bayesian Generative story IBM Model 3 (popular) translation (word substitution) fertility distortion (transposition) Complex model, makes inference very hard New translation model replace IBM Model 3 components with CRP processes 28
55 New Machine Translation without parallel data MT Decipherment (2) Bayesian Generative story IBM Model 3 (popular) translation (word substitution) fertility distortion (transposition) Complex model, makes inference very hard New translation model replace IBM Model 3 components with CRP processes 28 CRP cache model
56 Machine Translation without parallel data MT Decipherment (2) Bayesian (continued) Bayesian inference for estimating translation model efficient, scalable inference using strategies described earlier Sampling IBM Model 3 point-wise Gibbs sampling for each foreign string f, jointly sample alignments, e translations sampling operators = translate 1 word, swap alignments, (similar to German et al., 2001) blocked sampling sample single derivation for repeating sentences Choose the final sample as MT decipherment output 29
57 Machine Translation without parallel data Time Expressions English corpus 10 MONTHS LATER 10 MORE YEARS 24 MINUTES 28 CONSECUTIVE QUARTERS A WEEK EARLIER ABOUT A DECADE AGO ABOUT A MONTH AFTER AUGUST 6, 1789 CENTURIES AGO DEC. 11, 1989 TWO DAYS LATER TWO DECADES LATER TWO FULL DAYS YEARS 30 Spanish corpus 10 días consecutivos de cotización 10 semanas consecutivas 100 años después 17 de abril 1986 años cuarto puesto enero alrededor. 28 mil años antes mil años otros 12 meses más o menos una de tres horas uno de tres años un jueves por la noche Un día hace poco
58 Machine Translation without parallel data Time Expressions English corpus 10 MONTHS LATER 10 MORE YEARS 24 MINUTES 28 CONSECUTIVE QUARTERS A WEEK EARLIER ABOUT A DECADE AGO ABOUT A MONTH AFTER AUGUST 6, 1789 Results CENTURIES AGO DEC. 11, 1989 Baseline without parallel data TWO DAYS Decipherment LATER without parallel data TWO DECADES LATER TWO FULL DAYS YEARS 30 BLEU score Spanish corpus 10 días consecutivos de cotización 10 semanas consecutivas 100 años después 17 de abril 1986 años cuarto puesto enero alrededor. 28 Higher is better mil años antes mil años MOSES with parallel data 88 otros 12 meses más o menos una de tres 48.7horas uno de tres años un 18.2 jueves por la noche Un día hace poco
59 Machine Translation without parallel data English corpus Movie Subtitles ALL RIGHT, LET' S GO. ARE YOU ALL RIGHT? ARE YOU CRAZY? HEY, DO YOU WANT TO COME OUT AND PLAY THE GAME? WHAT ARE YOU DOING HERE? YEAH! YOU KNOW WHAT I MEAN? OPUS Spanish/English corpus [ Tiedemann, 2009 ] 31 Spanish corpus abran la puerta. bien hecho. por aquí! a qué te refieres? cómo podré verlos a través de mis lágrimas? oye, quieres salir y jugar el juego? un segundo. vamonos.
60 Machine Translation without parallel data English corpus Movie Subtitles ALL RIGHT, LET' S GO. ARE YOU ALL RIGHT? ARE YOU CRAZY? HEY, DO YOU WANT TO COME OUT AND PLAY THE GAME? WHAT ARE YOU DOING HERE? YEAH! YOU KNOW WHAT I MEAN? Results Decipherment without parallel data OPUS Spanish/English corpus [ Tiedemann, 2009 ] 31 BLEU score Spanish corpus abran la puerta Higher. is better bien hecho. 100 por aquí! a 75 qué te refieres? cómo podré MOSES verlos with a través parallel de mis data lágrimas 63.6? oye, quieres salir y jugar el juego? 50 un segundo. vamonos
61 MT Accuracy vs. Data Size Machine Translation without parallel data Phrase-based MT, parallel data MT quality on test set IBM Model 3 - distortion, parallel data EM Decipherment, no parallel data 32
62 MT Accuracy vs. Data Size Machine Translation without parallel data Phrase-based MT, parallel data MT quality on test set IBM Model 3 - distortion, parallel data EM Decipherment, no parallel data 32
63 Conclusion Language translation without parallel data very challenging task, but shown to be possible! (using decipherment approach) initial results promising can easily extend to new language pairs, domains Future Work Scalable decipherment methods for full-scale MT Better unsupervised algorithms for decipherment Leverage existing bilingual resources (e.g., dictionaries, etc.) during decipherment Applications for domain adaptation 33
64 What else can Decipherment Do? Language Translation This talk Monolingual corpora Spanish text English text TRAIN Translation tables associates/ asociados
65 What else can Decipherment Do? Language Translation This talk Monolingual corpora Spanish text English text TRAIN Translation tables associates/ asociados 0.8 Cryptanalysis CATCH A SERIAL KILLER Afternoon talk (2pm, Machine Learning Session 2-B) 34
66 NLP THANK YOU! 35
Chapter 5. Phrase-based models. Statistical Machine Translation
Chapter 5 Phrase-based models Statistical Machine Translation Motivation Word-Based Models translate words as atomic units Phrase-Based Models translate phrases as atomic units Advantages: many-to-many
Statistical Machine Translation Lecture 4. Beyond IBM Model 1 to Phrase-Based Models
p. Statistical Machine Translation Lecture 4 Beyond IBM Model 1 to Phrase-Based Models Stephen Clark based on slides by Philipp Koehn p. Model 2 p Introduces more realistic assumption for the alignment
SYSTRAN Chinese-English and English-Chinese Hybrid Machine Translation Systems for CWMT2011 SYSTRAN 混 合 策 略 汉 英 和 英 汉 机 器 翻 译 系 CWMT2011 技 术 报 告
SYSTRAN Chinese-English and English-Chinese Hybrid Machine Translation Systems for CWMT2011 Jin Yang and Satoshi Enoue SYSTRAN Software, Inc. 4444 Eastgate Mall, Suite 310 San Diego, CA 92121, USA E-mail:
Machine Translation. Agenda
Agenda Introduction to Machine Translation Data-driven statistical machine translation Translation models Parallel corpora Document-, sentence-, word-alignment Phrase-based translation MT decoding algorithm
Phrase-Based MT. Machine Translation Lecture 7. Instructor: Chris Callison-Burch TAs: Mitchell Stern, Justin Chiu. Website: mt-class.
Phrase-Based MT Machine Translation Lecture 7 Instructor: Chris Callison-Burch TAs: Mitchell Stern, Justin Chiu Website: mt-class.org/penn Translational Equivalence Er hat die Prüfung bestanden, jedoch
Statistical Machine Translation
Statistical Machine Translation Some of the content of this lecture is taken from previous lectures and presentations given by Philipp Koehn and Andy Way. Dr. Jennifer Foster National Centre for Language
SYSTRAN 混 合 策 略 汉 英 和 英 汉 机 器 翻 译 系 统
SYSTRAN Chinese-English and English-Chinese Hybrid Machine Translation Systems Jin Yang, Satoshi Enoue Jean Senellart, Tristan Croiset SYSTRAN Software, Inc. SYSTRAN SA 9333 Genesee Ave. Suite PL1 La Grande
Statistical NLP Spring 2008. Machine Translation: Examples
Statistical NLP Spring 2008 Lecture 11: Word Alignment Dan Klein UC Berkeley Machine Translation: Examples 1 Machine Translation Madame la présidente, votre présidence de cette institution a été marquante.
Convergence of Translation Memory and Statistical Machine Translation
Convergence of Translation Memory and Statistical Machine Translation Philipp Koehn and Jean Senellart 4 November 2010 Progress in Translation Automation 1 Translation Memory (TM) translators store past
The XMU Phrase-Based Statistical Machine Translation System for IWSLT 2006
The XMU Phrase-Based Statistical Machine Translation System for IWSLT 2006 Yidong Chen, Xiaodong Shi Institute of Artificial Intelligence Xiamen University P. R. China November 28, 2006 - Kyoto 13:46 1
Why Evaluation? Machine Translation. Evaluation. Evaluation Metrics. Ten Translations of a Chinese Sentence. How good is a given system?
Why Evaluation? How good is a given system? Machine Translation Evaluation Which one is the best system for our purpose? How much did we improve our system? How can we tune our system to become better?
Machine Translation. Why Evaluation? Evaluation. Ten Translations of a Chinese Sentence. Evaluation Metrics. But MT evaluation is a di cult problem!
Why Evaluation? How good is a given system? Which one is the best system for our purpose? How much did we improve our system? How can we tune our system to become better? But MT evaluation is a di cult
Computer Aided Translation
Computer Aided Translation Philipp Koehn 30 April 2015 Why Machine Translation? 1 Assimilation reader initiates translation, wants to know content user is tolerant of inferior quality focus of majority
Chapter 6. Decoding. Statistical Machine Translation
Chapter 6 Decoding Statistical Machine Translation Decoding We have a mathematical model for translation p(e f) Task of decoding: find the translation e best with highest probability Two types of error
Empirical Machine Translation and its Evaluation
Empirical Machine Translation and its Evaluation EAMT Best Thesis Award 2008 Jesús Giménez (Advisor, Lluís Màrquez) Universitat Politècnica de Catalunya May 28, 2010 Empirical Machine Translation Empirical
A Joint Sequence Translation Model with Integrated Reordering
A Joint Sequence Translation Model with Integrated Reordering Nadir Durrani, Helmut Schmid and Alexander Fraser Institute for Natural Language Processing University of Stuttgart Introduction Generation
Automatic Speech Recognition and Hybrid Machine Translation for High-Quality Closed-Captioning and Subtitling for Video Broadcast
Automatic Speech Recognition and Hybrid Machine Translation for High-Quality Closed-Captioning and Subtitling for Video Broadcast Hassan Sawaf Science Applications International Corporation (SAIC) 7990
Collecting Polish German Parallel Corpora in the Internet
Proceedings of the International Multiconference on ISSN 1896 7094 Computer Science and Information Technology, pp. 285 292 2007 PIPS Collecting Polish German Parallel Corpora in the Internet Monika Rosińska
An Iteratively-Trained Segmentation-Free Phrase Translation Model for Statistical Machine Translation
An Iteratively-Trained Segmentation-Free Phrase Translation Model for Statistical Machine Translation Robert C. Moore Chris Quirk Microsoft Research Redmond, WA 98052, USA {bobmoore,chrisq}@microsoft.com
CURRICULUM MAPPING. Content/Essential Questions for all Units
CURRICULUM MAPPING Subject: Spanish C Grade: 2 nd, 3 rd, 4 th Content/Essential Questions for all Units Students will participate in general conversation in Spanish Language Students will demonstrate knowledge
Exemplar for Internal Achievement Standard. Spanish Level 1
Exemplar for Internal Achievement Standard Spanish Level 1 This exemplar supports assessment against: Achievement Standard 90910 Interact using spoken Spanish to communicate personal information, ideas
Chapter 10 Physical Development from One to Three
Chapter 10 Chapter 10 Physical Development from One to Three Physical Development from One to Three Contents Section 10.1 Growth and Development from One to Three Section 10.2 Caring for Children from
THUTR: A Translation Retrieval System
THUTR: A Translation Retrieval System Chunyang Liu, Qi Liu, Yang Liu, and Maosong Sun Department of Computer Science and Technology State Key Lab on Intelligent Technology and Systems National Lab for
Customizing an English-Korean Machine Translation System for Patent Translation *
Customizing an English-Korean Machine Translation System for Patent Translation * Sung-Kwon Choi, Young-Gil Kim Natural Language Processing Team, Electronics and Telecommunications Research Institute,
The history of machine translation in a nutshell
1. Before the computer The history of machine translation in a nutshell 2. The pioneers, 1947-1954 John Hutchins [revised January 2014] It is possible to trace ideas about mechanizing translation processes
Overview of MT techniques. Malek Boualem (FT)
Overview of MT techniques Malek Boualem (FT) This section presents an standard overview of general aspects related to machine translation with a description of different techniques: bilingual, transfer,
Improving MT System Using Extracted Parallel Fragments of Text from Comparable Corpora
mproving MT System Using Extracted Parallel Fragments of Text from Comparable Corpora Rajdeep Gupta, Santanu Pal, Sivaji Bandyopadhyay Department of Computer Science & Engineering Jadavpur University Kolata
Tibetan-Chinese Bilingual Sentences Alignment Method based on Multiple Features
, pp.273-280 http://dx.doi.org/10.14257/ijdta.2015.8.4.27 Tibetan-Chinese Bilingual Sentences Alignment Method based on Multiple Features Lirong Qiu School of Information Engineering, MinzuUniversity of
Telling and asking for the time.
Lesson: : telling and asking for the time General: : Objectives: Structures: Target Vocab: 40 mins - 1 hour Telling and asking for the time. " Qué hora es?" "Por favor Podrías decirme la hora?" "Es la
Building a Web-based parallel corpus and filtering out machinetranslated
Building a Web-based parallel corpus and filtering out machinetranslated text Alexandra Antonova, Alexey Misyurev Yandex 16, Leo Tolstoy St., Moscow, Russia {antonova, misyurev}@yandex-team.ru Abstract
Statistical Machine Translation: IBM Models 1 and 2
Statistical Machine Translation: IBM Models 1 and 2 Michael Collins 1 Introduction The next few lectures of the course will be focused on machine translation, and in particular on statistical machine translation
Language and Computation
Language and Computation week 13, Thursday, April 24 Tamás Biró Yale University [email protected] http://www.birot.hu/courses/2014-lc/ Tamás Biró, Yale U., Language and Computation p. 1 Practical matters
DIPLOMADO DE JAVA - OCA
DIPLOMADO DE JAVA - OCA TABLA DE CONTENIDO INTRODUCCION... 3 ESTRUCTURA DEL DIPLOMADO... 4 Nivel I:... 4 Fundamentals of the Java Programming Language Java SE 7... 4 Introducing the Java Technology...
SUMMER WORK AP SPANISH LANGUAGE & CULTURE Bienvenidos a la clase de Español AP!
SUMMER WORK AP SPANISH LANGUAGE & CULTURE Bienvenidos a la clase de Español AP! To truly learn a language you have to use it as much as possible. The AP Exam focuses on the four communication skills: speaking,
Hybrid Machine Translation Guided by a Rule Based System
Hybrid Machine Translation Guided by a Rule Based System Cristina España-Bonet, Gorka Labaka, Arantza Díaz de Ilarraza, Lluís Màrquez Kepa Sarasola Universitat Politècnica de Catalunya University of the
The Prague Bulletin of Mathematical Linguistics NUMBER 93 JANUARY 2010 37 46. Training Phrase-Based Machine Translation Models on the Cloud
The Prague Bulletin of Mathematical Linguistics NUMBER 93 JANUARY 2010 37 46 Training Phrase-Based Machine Translation Models on the Cloud Open Source Machine Translation Toolkit Chaski Qin Gao, Stephan
Adaptive Development Data Selection for Log-linear Model in Statistical Machine Translation
Adaptive Development Data Selection for Log-linear Model in Statistical Machine Translation Mu Li Microsoft Research Asia [email protected] Dongdong Zhang Microsoft Research Asia [email protected]
The Impact of Morphological Errors in Phrase-based Statistical Machine Translation from English and German into Swedish
The Impact of Morphological Errors in Phrase-based Statistical Machine Translation from English and German into Swedish Oscar Täckström Swedish Institute of Computer Science SE-16429, Kista, Sweden [email protected]
Machine Translation and the Translator
Machine Translation and the Translator Philipp Koehn 8 April 2015 About me 1 Professor at Johns Hopkins University (US), University of Edinburgh (Scotland) Author of textbook on statistical machine translation
Wikipedia and Web document based Query Translation and Expansion for Cross-language IR
Wikipedia and Web document based Query Translation and Expansion for Cross-language IR Ling-Xiang Tang 1, Andrew Trotman 2, Shlomo Geva 1, Yue Xu 1 1Faculty of Science and Technology, Queensland University
Copyright 2016-123TeachMe.com 4ea67 1
Sentence Match Quiz for Category: hacer_make_do_1 1) Nosotros hacemos todo lo posible para proporcionar un buen servicio. - A: We do our best to provide good service. - B: These chores are done each time.
Teacher: Course Name: Spanish I Year. World Language Department Saugus High School Saugus Public Schools
Week 1 Week 2 Capítulo Preliminar 1. Intro to Spanish speaking world/nombres en Espanol 2. Frases útiles/ los cognados 3. El Alfabeto 4. Los Colores 5. Los números (0-30) and 1.3 Students present information,
Unit 2. This is my job
Unit 2. This is my job Exercise 1 a. Look at the photos and match them with the correct words from the box: An architect - an artist - a bank clerk - a dentist - a doctor - an electrician an engineer -
Be courteous and respectful. - treat others the way you would like to be treated.
Sra. Morales Be courteous and respectful - treat others the way you would like to be treated. Be prepared and on time - not only in class but with your assignments as well. Be a team player - help those
TS3: an Improved Version of the Bilingual Concordancer TransSearch
TS3: an Improved Version of the Bilingual Concordancer TransSearch Stéphane HUET, Julien BOURDAILLET and Philippe LANGLAIS EAMT 2009 - Barcelona June 14, 2009 Computer assisted translation Preferred by
Masconomet Regional High School Curriculum Guide
Masconomet Regional High School Curriculum Guide Course Title: Spanish II CP Course Number: 4311 Department: Foreign Languages Grade Level and Phase: 9 College Prep Length of Course: Year Course Description:
Getting Off to a Good Start: Best Practices for Terminology
Getting Off to a Good Start: Best Practices for Terminology Technologies for term bases, term extraction and term checks Angelika Zerfass, [email protected] Tools in the Terminology Life Cycle Extraction
How To Encrypt With A 64 Bit Block Cipher
The Data Encryption Standard (DES) As mentioned earlier there are two main types of cryptography in use today - symmetric or secret key cryptography and asymmetric or public key cryptography. Symmetric
The Transition of Phrase based to Factored based Translation for Tamil language in SMT Systems
The Transition of Phrase based to Factored based Translation for Tamil language in SMT Systems Dr. Ananthi Sheshasaayee 1, Angela Deepa. V.R 2 1 Research Supervisior, Department of Computer Science & Application,
FOR TEACHERS ONLY The University of the State of New York
FOR TEACHERS ONLY The University of the State of New York REGENTS HIGH SCHOOL EXAMINATION S COMPREHENSIVE EXAMINATION IN SPANISH Wednesday, January 24, 2007 9:15 a.m. to 12:15 p.m., only SCORING KEY Updated
Hybrid Strategies. for better products and shorter time-to-market
Hybrid Strategies for better products and shorter time-to-market Background Manufacturer of language technology software & services Spin-off of the research center of Germany/Heidelberg Founded in 1999,
tance alignment and time information to create confusion networks 1 from the output of different ASR systems for the same
1222 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 16, NO. 7, SEPTEMBER 2008 System Combination for Machine Translation of Spoken and Written Language Evgeny Matusov, Student Member,
Turker-Assisted Paraphrasing for English-Arabic Machine Translation
Turker-Assisted Paraphrasing for English-Arabic Machine Translation Michael Denkowski and Hassan Al-Haj and Alon Lavie Language Technologies Institute School of Computer Science Carnegie Mellon University
A New Input Method for Human Translators: Integrating Machine Translation Effectively and Imperceptibly
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015) A New Input Method for Human Translators: Integrating Machine Translation Effectively and Imperceptibly
Page 1. Session Overview: Cryptography
Cool Careers in Cyber Security Frequency Chart and Cipher Cryptography Delivery: Can be used as a table demo (hands-on) activity or during a presentation session. Best to have the wheels pre-made. Messaging
The Prague Bulletin of Mathematical Linguistics NUMBER 96 OCTOBER 2011 49 58. Ncode: an Open Source Bilingual N-gram SMT Toolkit
The Prague Bulletin of Mathematical Linguistics NUMBER 96 OCTOBER 2011 49 58 Ncode: an Open Source Bilingual N-gram SMT Toolkit Josep M. Crego a, François Yvon ab, José B. Mariño c c a LIMSI-CNRS, BP 133,
UM-Corpus: A Large English-Chinese Parallel Corpus for Statistical Machine Translation
UM-Corpus: A Large English-Chinese Parallel Corpus for Statistical Machine Translation Liang Tian 1, Derek F. Wong 1, Lidia S. Chao 1, Paulo Quaresma 2,3, Francisco Oliveira 1, Yi Lu 1, Shuo Li 1, Yiming
Systematic Comparison of Professional and Crowdsourced Reference Translations for Machine Translation
Systematic Comparison of Professional and Crowdsourced Reference Translations for Machine Translation Rabih Zbib, Gretchen Markiewicz, Spyros Matsoukas, Richard Schwartz, John Makhoul Raytheon BBN Technologies
New words to remember
Finanza Toolbox Materials What is a Bank Loan? Borrowing money from the bank is called a bank loan. People borrow money from the bank for many reasons. One reason to get a bank loan might be to buy a car.
Comprendium Translator System Overview
Comprendium System Overview May 2004 Table of Contents 1. INTRODUCTION...3 2. WHAT IS MACHINE TRANSLATION?...3 3. THE COMPRENDIUM MACHINE TRANSLATION TECHNOLOGY...4 3.1 THE BEST MT TECHNOLOGY IN THE MARKET...4
S P A N I S H G R A M M A R T I P S
S P A N I S H G R A M M A R T I P S One of the main impulses behind the earworms approach is to really get your brain used to the linguistic patterns, even the melody, of the target language. We do this
Statistical Machine Translation
Statistical Machine Translation What works and what does not Andreas Maletti Universität Stuttgart [email protected] Stuttgart May 14, 2013 Statistical Machine Translation A. Maletti 1 Main
FAMILY INDEPENDENCE ADMINISTRATION Seth W. Diamond, Executive Deputy Commissioner
FAMILY INDEPENDENCE ADMINISTRATION Seth W. Diamond, Executive Deputy Commissioner James K. Whelan, Deputy Commissioner Policy, Procedures and Training Lisa C. Fitzpatrick, Assistant Deputy Commissioner
Introduction. Philipp Koehn. 28 January 2016
Introduction Philipp Koehn 28 January 2016 Administrativa 1 Class web site: http://www.mt-class.org/jhu/ Tuesdays and Thursdays, 1:30-2:45, Hodson 313 Instructor: Philipp Koehn (with help from Matt Post)
First Year Spanish I SPAN 111 Summer 2015 MTWR
First Year Spanish I SPAN 111 Summer 2015 MTWR Instructor: Office: Office Hours: Email: Phone Number: Overview Bienvenidos! Welcome to Spanish 111, the first semester in UNR s Basic Spanish Language Program
Translation Solution for
Translation Solution for Case Study Contents PROMT Translation Solution for PayPal Case Study 1 Contents 1 Summary 1 Background for Using MT at PayPal 1 PayPal s Initial Requirements for MT Vendor 2 Business
Plan for: Preliminary Lessons Spanish Señora Franco
Plan for: Preliminary Lessons Spanish Señora Franco Pass Communication Standard 1.1: Interpersonal, 1.2: Interpretive, 1.3: Presentational Culture Standard 2.1, 2.2 Connection Standard 3.1, 3.2 Comparison
Composición 2: Narración Tema: Una experiencia inolvidable
Composición 2: Narración Tema: Una experiencia inolvidable Introduction Through your second composition, you ll continue to draw upon your personal world as a source of ideas for communicating ideas through
Multi-Engine Machine Translation by Recursive Sentence Decomposition
Multi-Engine Machine Translation by Recursive Sentence Decomposition Bart Mellebeek Karolina Owczarzak Josef van Genabith Andy Way National Centre for Language Technology School of Computing Dublin City
Ask your child what he or she is learning to say in Spanish at school. Encourage your child to act as if he or she is your teacher.
Welcome to Descubre el español con Santillana! This year, your child will be learning Spanish by exploring the culture of eight Spanish-speaking countries. Please join us as we travel through each of the
NLP Programming Tutorial 5 - Part of Speech Tagging with Hidden Markov Models
NLP Programming Tutorial 5 - Part of Speech Tagging with Hidden Markov Models Graham Neubig Nara Institute of Science and Technology (NAIST) 1 Part of Speech (POS) Tagging Given a sentence X, predict its
Response Area 3 - Community Meeting
September 2010 Greetings, Welcome to the Independence Division, Response Area 3 monthly community letter. Please check the Independence Division Response Area map at www.cmpd.org/patrol to see which area
Cryptography: Motivation. Data Structures and Algorithms Cryptography. Secret Writing Methods. Many areas have sensitive information, e.g.
Cryptography: Motivation Many areas have sensitive information, e.g. Data Structures and Algorithms Cryptography Goodrich & Tamassia Sections 3.1.3 & 3.1.4 Introduction Simple Methods Asymmetric methods:
Control of a variety of structures and idioms; occasional errors may occur, but
AP SPANISH LANGUAGE 2012 PRESENTATIONAL WRITING SCORING GUIDELINES SCORE DESCRIPTION TASK COMPLETION TOPIC DEVELOPMENT LANGUAGE USE 5 Demonstrates excellence 4 Demonstrates command 3 Demonstrates competence
PROMT Technologies for Translation and Big Data
PROMT Technologies for Translation and Big Data Overview and Use Cases Julia Epiphantseva PROMT About PROMT EXPIRIENCED Founded in 1991. One of the world leading machine translation provider DIVERSIFIED
Spanish 8695/S Paper 3 Speaking Test Teacher s Booklet Time allowed Instructions one not not Information exactly as they are printed not 8695/S
AQA Level 1/2 Certificate June 2014 Spanish 8695/S Paper 3 Speaking Test Teacher s Booklet To be conducted by the teacher-examiner between 24 April and 15 May 2014 Time allowed: 11 minutes (including 2
Translating the Penn Treebank with an Interactive-Predictive MT System
IJCLA VOL. 2, NO. 1 2, JAN-DEC 2011, PP. 225 237 RECEIVED 31/10/10 ACCEPTED 26/11/10 FINAL 11/02/11 Translating the Penn Treebank with an Interactive-Predictive MT System MARTHA ALICIA ROCHA 1 AND JOAN
An End-to-End Discriminative Approach to Machine Translation
An End-to-End Discriminative Approach to Machine Translation Percy Liang Alexandre Bouchard-Côté Dan Klein Ben Taskar Computer Science Division, EECS Department University of California at Berkeley Berkeley,
Digital Experience Day. Panorama actual. Madrid, Junio 2009. Oded Lida Greiss Director de la región Latina, Eyeblaster
Digital Experience Day Madrid, Junio 2009 Panorama actual Oded Lida Greiss Director de la región Latina, Eyeblaster Media - hace 90 años Radio Print Media - hace 60 años TV Radio Print Media - hace 30
AP SPANISH LANGUAGE 2011 PRESENTATIONAL WRITING SCORING GUIDELINES
AP SPANISH LANGUAGE 2011 PRESENTATIONAL WRITING SCORING GUIDELINES SCORE DESCRIPTION TASK COMPLETION TOPIC DEVELOPMENT LANGUAGE USE 5 Demonstrates excellence 4 Demonstrates command 3 Demonstrates competence
0678 FOREIGN LANGUAGE SPANISH (US)
UNIVERSITY OF CAMBRIDGE INTERNATIONAL EXAMINATIONS International General Certificate of Secondary Education MARK SCHEME for the May/June 2012 question paper for the guidance of teachers 0678 FOREIGN LANGUAGE
EVALUATING A FOREIGN LANGUAGE IN PRIMARY EDUCATION
REVISTTA ELLECTTRÓNI ICA INTTERNACI I IONALL ISSN I 11557766- -77880099 EVALUATING A FOREIGN LANGUAGE IN PRIMARY EDUCATION Plácido Bazo University of La Laguna [email protected] Marcos Peñate University
Automatic Mining of Internet Translation Reference Knowledge Based on Multiple Search Engines
, 22-24 October, 2014, San Francisco, USA Automatic Mining of Internet Translation Reference Knowledge Based on Multiple Search Engines Baosheng Yin, Wei Wang, Ruixue Lu, Yang Yang Abstract With the increasing
Chapter 23. Database Security. Security Issues. Database Security
Chapter 23 Database Security Security Issues Legal and ethical issues Policy issues System-related issues The need to identify multiple security levels 2 Database Security A DBMS typically includes a database
IRIS - English-Irish Translation System
IRIS - English-Irish Translation System Mihael Arcan, Unit for Natural Language Processing of the Insight Centre for Data Analytics at the National University of Ireland, Galway Introduction about me,