(Statistical Machine Translation: SMT[1]) [2]

Σχετικά έγγραφα
(Statistical Machine Translation: SMT [1])

1 n-gram n-gram n-gram [11], [15] n-best [16] n-gram. n-gram. 1,a) Graham Neubig 1,b) Sakriani Sakti 1,c) 1,d) 1,e)

1530 ( ) 2014,54(12),, E (, 1, X ) [4],,, α, T α, β,, T β, c, P(T β 1 T α,α, β,c) 1 1,,X X F, X E F X E X F X F E X E 1 [1-2] , 2 : X X 1 X 2 ;

(String-to-Tree ) KJ [11] best 1-best 2. SMT 2. [9] Brockett [2] Mizumoto [10] Brockett [2] [10] [15] ê = argmax e P(e f ) = argmax e M m=1 λ

[15], [16], [17] [6] [2] [5] Jiang [6] 2.1 [6], [10] Score(x, y) y ( 1) ( 1 ) b e ( 1 ) b e. O(n 2 ) Jiang [6] (word lattice reranking)

,.,,., [1], [3], [4], [5] [6]. [2]. ,,, Tree-to-String. 1,f) input 1 (Python) : if x % 5 == 0: output 2 (Comment): # y x 5

An Analysis of Problems in Grammatical Error Correction of ESL Writings Using a Large Learner Corpus of English

Η Αυτοματοποιημένη και μη-αυτοματοποιημένη αξιολόγηση συστήματος Στατιστικής Μηχανικής Μετάφρασης για το γλωσσικό ζεύγος Ελληνικά - Ιταλικά

Faruqui [7] WordNet [15] FrameNet [2] PPDB [8]

A hybrid approach to compiling bilingual dictionaries of medical terms from parallel corpora

Buried Markov Model Pairwise

ΟΙΚΟΝΟΜΙΚΟ ΠΑΝΕΠΙΣΤΗΜΙΟ ΑΘΗΝΩΝ ΠΡΟΓΡΑΜΜΑ ΜΕΤΑΠΤΥΧΙΑΚΩΝ ΣΠΟΥΔΩΝ ΣΤΗΝ ΕΠΙΣΤΗΜΗ ΤΩΝ ΥΠΟΛΟΓΙΣΤΩΝ. Διπλωματική Εργασία Μεταπτυχιακού Διπλώματος Ειδίκευσης

The State of the Art and Difficulties in Automatic Chinese Word Segmentation

ΟΙΚΟΝΟΜΙΚΟ ΠΑΝΕΠΙΣΤΗΜΙΟ ΑΘΗΝΩΝ ΤΜΗΜΑ ΠΛΗΡΟΦΟΡΙΚΗΣ

IPSJ SIG Technical Report Vol.2014-CE-127 No /12/6 CS Activity 1,a) CS Computer Science Activity Activity Actvity Activity Dining Eight-He

3: A convolution-pooling layer in PS-CNN 1: Partially Shared Deep Neural Network 2.2 Partially Shared Convolutional Neural Network 2: A hidden layer o

1,a) 1,b) 2 3 Sakriani Sakti 1 Graham Neubig 1 1. A Study on HMM-Based Speech Synthesis Using Rich Context Models

GPGPU. Grover. On Large Scale Simulation of Grover s Algorithm by Using GPGPU

Re-Pair n. Re-Pair. Re-Pair. Re-Pair. Re-Pair. (Re-Merge) Re-Merge. Sekine [4, 5, 8] (highly repetitive text) [2] Re-Pair. Blocked-Repair-VF [7]

Stabilization of stock price prediction by cross entropy optimization


[4] 1.2 [5] Bayesian Approach min-max min-max [6] UCB(Upper Confidence Bound ) UCT [7] [1] ( ) Amazons[8] Lines of Action(LOA)[4] Winands [4] 1

Quick algorithm f or computing core attribute

No. 7 Modular Machine Tool & Automatic Manufacturing Technique. Jul TH166 TG659 A

An Automatic Modulation Classifier using a Frequency Discriminator for Intelligent Software Defined Radio

SocialDict. A reading support tool with prediction capability and its extension to readability measurement

S.Piperidis, S. Boutsis, J. Demiros

ΠΟΛΥΤΙΜΟ. Ερευνητικό έργο. της Ε. Γαλιώτου*

MIDI [8] MIDI. [9] Hsu [1], [2] [10] Salamon [11] [5] Song [6] Sony, Minato, Tokyo , Japan a) b)

[5] F 16.1% MFCC NMF D-CASE 17 [5] NMF NMF 3. [5] 1 NMF Deep Neural Network(DNN) FUSION 3.1 NMF NMF [12] S W H 1 Fig. 1 Our aoustic event detect

Vol. 31,No JOURNAL OF CHINA UNIVERSITY OF SCIENCE AND TECHNOLOGY Feb

Applying Markov Decision Processes to Role-playing Game

Web-based supplementary materials for Bayesian Quantile Regression for Ordinal Longitudinal Data

Fourier transform, STFT 5. Continuous wavelet transform, CWT STFT STFT STFT STFT [1] CWT CWT CWT STFT [2 5] CWT STFT STFT CWT CWT. Griffin [8] CWT CWT

HIV HIV HIV HIV AIDS 3 :.1 /-,**1 +332

GPU. CUDA GPU GeForce GTX 580 GPU 2.67GHz Intel Core 2 Duo CPU E7300 CUDA. Parallelizing the Number Partitioning Problem for GPUs

( ) , ) , ; kg 1) 80 % kg. Vol. 28,No. 1 Jan.,2006 RESOURCES SCIENCE : (2006) ,2 ,,,, ; ;

: Monte Carlo EM 313, Louis (1982) EM, EM Newton-Raphson, /. EM, 2 Monte Carlo EM Newton-Raphson, Monte Carlo EM, Monte Carlo EM, /. 3, Monte Carlo EM

{takasu, Conditional Random Field

2016 IEEE/ACM International Conference on Mobile Software Engineering and Systems

CSJ. Speaker clustering based on non-negative matrix factorization using i-vector-based speaker similarity

«ΑΝΑΠΣΤΞΖ ΓΠ ΚΑΗ ΥΩΡΗΚΖ ΑΝΑΛΤΖ ΜΔΣΔΩΡΟΛΟΓΗΚΩΝ ΓΔΓΟΜΔΝΩΝ ΣΟΝ ΔΛΛΑΓΗΚΟ ΥΩΡΟ»

552 Lee (2006),,, BIC,. : ; ; ;. 2., Poisson (Zero-Inflated Poisson Distribution), ZIP. Y ZIP(φ, λ), φ + (1 φ) exp( λ), y = 0; P {Y = y} = (1 φ) exp(

90 [, ] p Panel nested error structure) : Lagrange-multiple LM) Honda [3] LM ; King Wu, Baltagi, Chang Li [4] Moulton Randolph ANOVA) F p Panel,, p Z

Chinese Journal of Applied Probability and Statistics Vol.28 No.3 Jun (,, ) 应用概率统计 版权所用,,, EM,,. :,,, P-. : O (count data)

Chap. 6 Pushdown Automata

: Active Learning 2017/11/12

Text Mining using Linguistic Information

ΟΡΓΑΝΙΣΜΟΣ ΒΙΟΜΗΧΑΝΙΚΗΣ ΙΔΙΟΚΤΗΣΙΑΣ

(2), ,. 1).

Research of Han Character Internal Codes Recognition Algorithm in the Multi2lingual Environment

substructure similarity search using features in graph databases

Vol.4-DCC-8 No.8 Vol.4-MUS-5 No.8 4// 3 3 Hanning (T ) 3 Hanning 3T (y(t)w(t)) dt =.5 T y (t)dt. () STRAIGHT F 3 TANDEM-STRAIGHT[] 3 F F 3 [] F []. :

Bundle Adjustment for 3-D Reconstruction: Implementation and Evaluation

Maxima SCORM. Algebraic Manipulations and Visualizing Graphs in SCORM contents by Maxima and Mashup Approach. Jia Yunpeng, 1 Takayuki Nagai, 2, 1

Ηλεκτρονικά σώματα κειμένων και γλωσσική διδασκαλία: Διεθνείς αναζητήσεις και διαφαινόμενες προοπτικές για την ελληνική γλώσσα

Development and Verification of Multi-Level Sub- Meshing Techniques of PEEC to Model High- Speed Power and Ground Plane-Pairs of PFBS

ECONOMIA MONETARIA (parte generale) Prof. Guido Ascari LEZIONE 3 LA DOMANDA DI MONETA

Retrieval of Seismic Data Recorded on Open-reel-type Magnetic Tapes (MT) by Using Existing Devices

Tree Transformations and Dependencies

Japanese Fuzzy String Matching in Cooking Recipes

FX10 SIMD SIMD. [3] Dekker [4] IEEE754. a.lo. (SpMV Sparse matrix and vector product) IEEE754 IEEE754 [5] Double-Double Knuth FMA FMA FX10 FMA SIMD

2 ~ 8 Hz Hz. Blondet 1 Trombetti 2-4 Symans 5. = - M p. M p. s 2 x p. s 2 x t x t. + C p. sx p. + K p. x p. C p. s 2. x tp x t.

n 1 n 3 choice node (shelf) choice node (rough group) choice node (representative candidate)

Cite as: Pol Antras, course materials for International Economics I, Spring MIT OpenCourseWare ( Massachusetts

Αγορά Ακινήτων και η ελληνική Κρίση

Curran et al.,**. Davies et al ,**, ,***,**/

Optimization, PSO) DE [1, 2, 3, 4] PSO [5, 6, 7, 8, 9, 10, 11] (P)

* ** *** *** Jun S HIMADA*, Kyoko O HSUMI**, Kazuhiko O HBA*** and Atsushi M ARUYAMA***

Εξόρυξη Γνώμης: Δημιουργία Ελληνικού Λεξικού Πόρου

ARISTOTLE UNIVERSITY OF THESSALONIKI FACULTY OF FORESTRY AND NATURAL ENVIRONMENT Institute of Mountainous Water Management and Control

:,,,, ,,, ;,,,,,, ,, (Barro,1990), (Barro and Sala2I2Martin,1992), (Arrow and Kurz,1970),, ( Glomm and Ravikumar,1994), (Solow,1957)

Γενικό ποσοστό συμμετοχής στην αγορά εργασίας πληθυσμού χρονών - σύνολο

IF(Ingerchange Format) [7] IF C-STAR(Consortium for speech translation advanced research ) [8] IF 2 IF

Development of the Nursing Program for Rehabilitation of Woman Diagnosed with Breast Cancer

Αξιολόγηση των εκπαιδευτικών δραστηριοτήτων των νοσοκομειακών βιβλιοθηκών.

Γενικό ποσοστό απασχόλησης ισοδύναμου πλήρως απασχολούμενου πληθυσμού - σύνολο

Chapter 1 Introduction to Observational Studies Part 2 Cross-Sectional Selection Bias Adjustment

A research on the influence of dummy activity on float in an AOA network and its amendments

Γενικός ρυθμός μεταβολής οικονομικά ενεργού πληθυσμού χρονών - σύνολο

RMT Tick RMT. Application of the RMT-test on Real Data: Hash Function and Tick Data of Stock Prices

Study on Re-adhesion control by monitoring excessive angular momentum in electric railway traction

Εκτεταμένη περίληψη Περίληψη

Resurvey of Possible Seismic Fissures in the Old-Edo River in Tokyo

Τεχνολογία Ψυχαγωγικού Λογισμικού και Εικονικοί Κόσμοι Ενότητα 8η - Εικονικοί Κόσμοι και Πολιτιστικό Περιεχόμενο

Ποσοστό απασχόλησης στον τριτογενή τομέα του πληθυσμού χρονών - σύνολο

Η ΔΙΔΑΣΚΑΛΙΑ ΤΟΥ ΕΛΛΗΝΙΚΟΥ ΛΑΪΚΟΥ ΠΑΡΑΔΟΣΙΑΚΟΥ ΧΟΡΟΥ 1 ΣΤΑ ΣΥΓΧΡΟΝΑ ΕΚΠΑΙΔΕΥΤΙΚΑ ΠΛΑΙΣΙΑ

ΕΚΤΙΜΗΣΗ ΤΟΥ ΚΟΣΤΟΥΣ ΤΩΝ ΟΔΙΚΩΝ ΑΤΥΧΗΜΑΤΩΝ ΚΑΙ ΔΙΕΡΕΥΝΗΣΗ ΤΩΝ ΠΑΡΑΓΟΝΤΩΝ ΕΠΙΡΡΟΗΣ ΤΟΥ

clearing a space (focusing) clearing a space, CS CS CS experiencing I 1. E. T. Gendlin (1978) experiencing (Gendlin 1962) experienc-

Study of urban housing development projects: The general planning of Alexandria City

Ποσοστό μακροχρόνιας ανεργίας (διάρκεια 12+ μήνες) οικονομικά ενεργού πληθυσμού 15+ χρονών - σύνολο

Probabilistic Approach to Robust Optimization

ΥΠΕΡΕΙΑ ΤΟΜΟΣ ΕΚΤΟΣ. ΠΡΑΚΤΙΚΑ ΣΤ ΙΕΘΝΟΥΣ ΣΥΝΕ ΡΙΟΥ «ΦΕΡΑΙ-ΒΕΛΕΣΤΙΝΟ-ΡΗΓΑΣ» Βελεστίνο, 4-7 Οκτωβρίου 2012 MEΡΟΣ B ΡΗΓΑΣ

CAP A CAP

ΔΙΠΛΩΜΑΤΙΚΕΣ ΕΡΓΑΣΙΕΣ

Architecture οf Integrated Ιnformation Systems (ARIS)

ΘΕΜΑΤΙΚΗ ΕΥΡΕΤΗΡΙΑΣΗ ΚΑΙ ΚΑΘΙΕΡΩΣΗ ΟΡΟΛΟΓΙΑΣ ΣΤΙΣ ΤΕΧΝΙΚΕΣ ΒΙΒΛΙΟΘΗΚΕΣ: Η ΕΜΠΕΙΡΙΑ ΣΤΟ ΤΕΕ

Toward a SPARQL Query Execution Mechanism using Dynamic Mapping Adaptation -A Preliminary Report- Takuya Adachi 1 Naoki Fukuta 2.

High order interpolation function for surface contact problem

Μερίδιο εργοδοτουμένων με μερική ή / και προσωρινή απασχόληση στον εργοδοτούμενο πληθυσμό 15+ χρονών - σύνολο

Transcript:

1,a) Graham Neubig 1,b) Sakriani Sakti 1,c) 1,d) 1,e) 2 1. (Statistical Machine Translation: SMT[1]) [2] [3] [4][5][6] 2 1 (a) 3 approach 1 Nara Institute of Science and Technology a) miura.akiba.lr9@is.naist.jp b) neubig@is.naist.jp c) ssakti@is.naist.jp d) tomoki@is.naist.jp e) s-nakamura@is.naist.jp 1 (a) ( - - ) (b) (c) 1(b) 1(c) c 2015 Information Processing Society of Japan 1

(Synchronous Context-free Grammar: SCFG[7]) (Multi-Synchronous CFG: MSCFG[8]) MSCFG SCFG SCFG MSCFG Europarl 4 2. 2.1 (Hierarchical Phrase-Based Translation: Hiero[7]) SCFG SCFG X s, t (1) X s t s t X X 0 of X 1,X 1 X 0 (2) Chiang SCFG SCFG φ(s t), φ(t s) φ lex (s t), φ lex (t s) (t ) ( 1) 6 CKY+ [9] [7] 2.2 MSCFG[8] SCFG SCFG t MSCFG N X s, t 1,..., t N (3) MSCFG SCFG MSCFG SCFG Neubig MSCFG 2 SCFG MSCFG 3. SMT 3 (Cascade): [3] (Synthetic): [3] (Triangulation): [4] [5] c 2015 Information Processing Society of Japan 2

3.1 Cohn [4] ( ) T SP, T PT T SP, T PT s, p, p, t p X s, t (4) φ( ) φ lex ( ) T ST φ ( t s ) = φ ( t p ) φ (p s) (5) φ ( s t ) = φ (s p) φ ( p t ) (6) ( ) ( ) φ lex t s = φ lex t p φlex (p s) (7) ( ) φ lex s t = (8) φ lex (s p) φ lex ( p t ) (5)-(8) φ ( t p, s ) = φ ( t p ) (9) φ ( s p, t ) = φ (s p) (10) 3.2 p SCFG MSCFG X s, t, p (11) (5)-(8) φ(t, p s), φ(s p, t) φ ( t, p s ) = φ ( t p ) φ (p s) (12) φ ( s p, t ) = φ (s p) (13) φ(p s) φ(s p) φ lex (p s) φ lex (s p) T SP 10 t p 2 1 13 MSCFG s, t s, t, p Neubig T 1 T 2 T 1 - [8] s T 1 φ(t 1 s) L t 1 t 1 φ(t 1, t 2 s) t 2 4. 4.1 Europarl [10] (en) (de), (es), (fr), (it) 4 5 Gale-Church [11] 90 1,500 10 10 200 Travatar [12] Hiero SCFG BLEU [13] MERT[14] BLEU MSCFG L = 20 T 1 MSCFG 6 c 2015 Information Processing Society of Japan 3

BLEU Score [%] Source Target Tri. SCFG Tri. MSCFG Tri. MSCFG Tri. MSCFG Direct Cascade (baseline) -PivotLM +PivotLM 100k +PivotLM 2M es 27.10 25.05 25.31 25.38 25.52 25.75 de fr 25.65 23.86 24.12 24.16 24.25 24.58 it 23.04 20.76 21.27 21.42 21.65 22.29 de 20.11 18.52 18.77 18.97 19.08 19.40 es fr 33.48 27.00 29.54 29.87 29.91 29.95 it 27.82 22.57 25.11 25.01 25.18 25.64 de 19.69 18.01 18.73 18.77 18.87 19.19 fr es 34.36 27.26 30.31 30.53 30.73 31.00 it 28.48 22.73 25.31 25.50 25.72 26.22 de 19.09 14.03 17.35 17.99 18.17 18.52 it es 31.99 25.64 28.85 28.83 29.01 29.31 fr 31.39 25.87 28.48 28.40 28.63 29.02 1 BLEU ( : p<0.05, : p<0.01) Direct: SCFG Cascade: SCFG Tri. SCFG: SCFG SCFG Tri. MSCFG: SCFG MSCFG -Pivot +PivotLM 100k/2M 10 200 4.2 1 BLEU 200 0.4 1.2 BLEU BLEU Score [%] Direct Tri. SCFG Tri. MSCFG 23.2 23 22.8 22.6 22.4 22.2 22 21.8 21.6 21.4 21.2 0 500000 1x10 6 1.5x10 6 2x10 6 Pivot-LM Size [sent.] 2 ( - ) MSCFG SCFG 2 c 2015 Information Processing Society of Japan 4

( ): ich bedaure, daß es keine gemeinsame annäherung gegeben hat. ( ): sono spiacente del mancato approccio comune. Tri. SCFG: mi rammarico per il fatto che non si ravvicinamento comune. (BLEU+1: 13.84) Tri. MSCFG+PivotLM 2M: mi dispiace che non esiste un approccio comune. (BLEU+1: 25.10) i regret that there is no common approach. (Generated English Sentence) Tri. MSCFG+PivotLM 2M MSCFG approccio approach 5. 2 SCFG 1 MSCFG MSCFG Microsoft CORE [6] Xiaoning Zhu, Zhongjun He, Hua Wu, Conghui Zhu, Haifeng Wang, and Tiejun Zhao. Improving Pivot-Based Statistical Machine Translation by Pivoting the Cooccurrence Count of Phrase Pairs. In Proc. EMNLP, 2014. [7] David Chiang. Hierarchical phrase-based translation. Computational Linguistics, Vol. 33, No. 2, pp. 201 228, 2007. [8] Graham Neubig, Philip Arthur, and Kevin Duh. Multi- Target Machine Translation with Multi-Synchronous Context-free Grammars. In Proc. NAACL, 2015. [9] Jean-Cédric Chappelier, Martin Rajman, et al. A Generalized CYK Algorithm for Parsing Stochastic CFG. TAPD, Vol. 98, No. 133-137, p. 5, 1998. [10] Philipp Koehn. Europarl: A parallel corpus for statistical machine translation. In MT summit, Vol. 5, pp. 79 86, 2005. [11] William A Gale and Kenneth W Church. A program for aligning sentences in bilingual corpora. Computational linguistics, Vol. 19, No. 1, pp. 75 102, 1993. [12] Graham Neubig. Travatar: A Forest-to-String Machine Translation Engine based on Tree Transducers. In Proc. ACL Demo Track, pp. 91 96, 2013. [13] Kishore Papineni, Salim Roukos, Todd Ward, and Wei- Jing Zhu. BLEU: a method for automatic evaluation of machine translation. In Proc. ACL, pp. 311 318, 2002. [14] Franz Josef Och. Minimum Error Rate Training in Statistical Machine Translation. In Proc. ACL, pp. 160 167, 2003. [1] Peter F. Brown, Vincent J.Della Pietra, Stephen A. Della Pietra, and Robert L. Mercer. The Mathematics of Statistical Machine Translation: Parameter Estimation. Computational Linguistics, Vol. 19, pp. 263 312, 1993. [2] Christopher Dyer, Aaron Cordova, Alex Mont, and Jimmy Lin. Fast, easy, and cheap: construction of statistical machine translation models with MapReduce. In Proc. WMT, pp. 199 207, 2008. [3] Adrià de Gispert and José B. Mariño. Catalan-English Statistical Machine Translation without Parallel Corpus: Bridging through Spanish. In Proc. of LREC 5th Workshop on Strategies for developing machine translation for minority languages, 2006. [4] Trevor Cohn and Mirella Lapata. Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora. In Proc. ACL, pp. 728 735, June 2007. [5] Masao Utiyama and Hitoshi Isahara. A Comparison of Pivot Methods for Phrase-Based Statistical Machine Translation. In Proc. NAACL, pp. 484 491, 2007. c 2015 Information Processing Society of Japan 5