Vol. 23 No. 5 December (Rule-Based Machine Translation; RBMT (Nirenburg 1989)) 2 (Statistical Machine Translation; SMT (Brown, Pietra, Piet
|
|
|
- しょうこ えんの
- 5 years ago
- Views:
Transcription
1 Graham Neubig, Sakriani Sakti 2 Improving Pivot Translation by Remembering the Pivot Akiva Miura, Graham Neubig,, Sakriani Sakti, Tomoki Toda and Satoshi Nakamura In statistical machine translation, the pivot translation approach allows for translation of language pairs with little or no parallel data by introducing a third language for which data exists. In particular, the triangulation method, which translates by combining source-pivot and pivot-target translation models into a source-target model is known for its high translation accuracy. However, in the conventional triangulation method, information of pivot phrases is forgotten, and not used in the translation process. In this research, we propose a novel approach to remember the pivot phrases in the triangulation stage, and use a pivot language model as an additional information source at translation phase. Experimental results on the united nations parallel corpus showed significant improvements in all tested combinations of languages. Key Words: Statistical Machine Translation, Multilinguality, Pivot Translation, Synchronous Context-Free Grammars, Language Models, Parallel Corpora, Graduate School of Information Science, Nara Institute of Science and Technology, Language Technologies Institute, Carnegie Mellon University, Information Technology Center, Nagoya University
2 Vol. 23 No. 5 December (Rule-Based Machine Translation; RBMT (Nirenburg 1989)) 2 (Statistical Machine Translation; SMT (Brown, Pietra, Pietra, and Mercer 1993)) 2 SMT (Dyer, Cordova, Mont, and Lin 2008) (Pvt) (de Gispert and Mariño 2006; Cohn and Lapata 2007; Zhu, He, Wu, Zhu, Wang, and Zhao 2014) 2 (Cascade Translation (de Gispert and Mariño 2006)) (Src-Pvt) (Pvt-Trg) 2 SMT (Src-Trg) SMT (Triangulation (Cohn and Lapata 2007)) (Utiyama and Isahara 2007) SMT (Phrase-Based Machine Translation; PBMT (Koehn, Och, and Marcu 2003)) 500
3 Neubig Sakti, 1 2 PBMT SMT (Synchronous Context-Free Grammar; SCFG (Chiang 2007)) SMT PBMT PBMT SCFG Src-Trg Src-Pvt Pvt-Trg Src-Trg 1 (a) (b) (c) (d) 1(c) Src-Trg
4 Vol. 23 No. 5 December PBMT SMT 1.1 PBMT SMT SCFG SCFG PBMT 1 2 1(c) 1.1 SMT SMT 1 2 SMT 2.1 SMT PBMT, 2.2 SCFG, 2.3 SCFG 3 Multi-Synchronous Context-Free Grammar; MSCFG, ( Neubig Sakti 2014, 2015) ACL 2015: The 53rd Annual Meeting of the Association for Computational Linguistics (Miura, Neubig, Sakti, Toda, and Nakamura 2015) 502
5 Neubig Sakti, 2.1 SMT (Shannon 1948) f E(f) f e E(f) P r(e f) e SMT P r(e f) ê E(f) ê = arg max P r(e f) (1) e E(f) = arg max e E(f) P r(f e)p r(e) P r(f) = arg max P r(f e)p (e) (3) e E(f) (Och 2003) ê = arg max P r(e f) (4) e E(f) arg max e E(f) exp ( w T h(f, e ) e exp (w T h(f, e )) = arg max w T h(f, e) (6) e E(f) h P r(e) P r(f e) SMT w h w BLEU(Papineni, Roukos, Ward, and Zhu 2002) (Och 2003) 2.2 (2) (5) 503
6 Vol. 23 No. 5 December Koehn (PBMT (Koehn et al. 2003)) SMT PBMT (Brown et al. 1993) PBMT PBMT (6) PBMT 2 (Goto, Utiyama, Sumita, Tamura, and Kurohashi 2013)
7 Neubig Sakti, 2.3 SMT (SCFG (Chiang 2007)) SCFG (Hierarchical Phrase-Based Translation; Hiero (Chiang 2007)) SCFG X s, t (7) X s t s t X X 0 of X 1, X 1 X 0 (8) Hiero SCFG PBMT X i SCFG 2 X X 0 hit X 1., X 0 X 1 (9) X John, (10) X a ball, (11) S S X 0, X 0 S = X 0, X 0 (12) = X 1 hit X 2., X 1 X 2 (13) = John hit X 2., X 2 (14) = John hit a ball., (15) SCFG ϕ(s t) ϕ(t s) ϕ lex (s t) ϕ lex (t s) t
8 Vol. 23 No. 5 December 2016 CKY+ (Chappelier and Rajman 1998) (Chiang 2007) 2.4 SCFG (MSCFG (Neubig, Arthur, and Duh 2015)) SCFG t MSCFG N X s, t 1,, t N (16) MSCFG SCFG 3 1 N 1 SCFG PBMT MSCFG 3 3 PBMT MSCFG 506
9 Neubig Sakti, 3 2 SMT SMT SMT 100 SMT PBMT 4 PBMT SCFG Src Trg Pvt Src-Pvt, Src-Trg, Pvt-Trg 3.1 (Cascade) (de Gispert and Mariño 2006) Src Trg 4 Src-Pvt, Pvt-Trg Src Pvt Pvt Trg Src Trg 4 507
10 Vol. 23 No. 5 December 2016 PBMT 2 Src-Pvt n Pvt-Trg (Utiyama and Isahara 2007) n 3.2 Src-Trg SMT (Synthetic) (de Gispert and Mariño 2006) Src-Trg 5 Src-Pvt, Pvt-Trg Pvt-Trg SMT Src-Pvt Pvt Pvt-Trg Src-Trg Src-Trg SMT SMT De Gispert (de Gispert and Mariño 2006) 5 508
11 Neubig Sakti, 3.3 PBMT SCFG Src-Trg 6 Cohn (Triangulation) (Cohn and Lapata 2007) Src-Pvt Pvt-Trg T SP, T P T T SP, T P T Src-Trg T ST T ST ϕ( ) ϕ lex ( ) ϕ ( t s ) ( ) = ϕ t p ϕ (p s) (17) p T SP T P T ϕ ( s t ) ( ) = ϕ (s p) ϕ p t (18) p T SP T P T ( ) ( ) ϕ lex t s = t p ϕlex (p s) (19) p T SP T P T ϕ lex ( ) ( ) ϕ lex s t = ϕ lex (s p) ϕ lex p t p T SP T P T (20) s, p, t Src, Pvt, Trg p T SP T P T p T SP, T P T (17) (20) ϕ ( t p, s ) = ϕ ( t p ) (21) ϕ ( s p, t ) = ϕ (s p) (22) 6 509
12 Vol. 23 No. 5 December 2016 Utiyama (Utiyama and Isahara 2007) n = 1 n = 15 BLEU 4 3 SMT SCFG SMT PBMT SCFG (7) SCFG PBMT PBMT SCFG 4.1 SCFG Src-Pvt, Pvt-Trg 2.3 Src-Pvt, Pvt-Trg Pvt X s, p, X p, t X s, t (17) (20) PBMT s, p, t SCFG X s, t X p, t PBMT PBMT 510
13 Neubig Sakti, SCFG (Ziemski, Junczys-Dowmunt, and Pouliquen 2016) (En) (Ar) (Es) (Fr) (Ru) (Zh) 6 1,100 6 SMT 5 Src-Pvt Pvt-Trg Src-Trg Pvt (train) 1,100 (test) 4,000 (dev) 4,000 train 60 test, dev 80 train 800 test, dev 3,800 train Src-Pvt train1 Pvt-Trg train2 10 test dev 1,500 PBMT SCFG SMT Direct Pvt Src-Trg train1 train2 train1, train2 Direct 1 Direct 2 Direct 1 / 2 Cascade Src-Pvt, Pvt-Trg train1 train2 Src-Trg Triangulation Src-Pvt, Pvt-Trg train1, train2 Src-Trg KyTea (Neubig, Nakata, 511
14 Vol. 23 No. 5 December 2016 and Mori 2011) PBMT Moses (Koehn, Hoang, Birch, Callison-Burch, Federico, Bertoldi, Cowan, Shen, Moran, Zens, Dyer, Bojar, Constantin, and Herbst 2007) SCFG Travatar (Neubig 2013) Hiero KenLM (Heafield 2011) train1+train gram BLEU (Papineni et al. 2002) SMT MERT (Och 2003) BLEU 4.3 Direct 1 / 2, Triangulation, Cascade 1 PBMT Triangulation Cascade 4.1 SCFG Triangulation Cascade SMT Triangulation Cascade Triangulation Direct Hiero Direct BLEU Triangulation BLEU Direct Triangulation Direct BLEU 15 Triangulation Hiero Triangulation Direct PBMT Hiero Hiero PBMT Hiero Triangulation PBMT 0.5 BLEU Hiero 512
15 Neubig Sakti, 1 Source Target MT Method Ar Es Fr Ru Zh Es Fr Ru Zh Ar Fr Ru Zh Ar Es Ru Zh Ar Es Fr Zh Ar Es Fr Ru BLEU Score (%) Direct 1 / 2 Triangulation Cascade PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT 8.93 / Hiero / PBMT / Hiero / PBMT / Hiero / PBMT / Hiero /
16 Vol. 23 No. 5 December Europarl (Koehn 2005) Europarl 10 1,500 Src-Pvt Pvt-Trg 4.3 PBMT Hiero Triangulation Cascade 2 Triangulation Direct PBMT Hiero PBMT PBMT SCFG SCFG PBMT PBMT (Utiyama and Isahara 2007) 1 (Zhu et al. 2014) (Levinboim and Chiang 2015) 514
17 Neubig Sakti, (Dabre, Cromieres, Kurohashi, and Bhattacharyya 2015) 5 3 SMT 4 SCFG SCFG PBMT Src-Trg Src-Pvt, Pvt-Trg Src-Trg Src-Trg 7 3 approach Src-Trg 8 Src Trg Pvt
18 Vol. 23 No. 5 December 2016 Src-Trg Pvt 5.2 Src Trg Pvt Src Trg Pvt 9 SCFG 2.3 MSCFG 2.4 MSCFG Src-Pvt, Pvt-Trg SCFG SCFG Src-Trg-Pvt MSCFG Pvt
19 Neubig Sakti, SCFG MSCFG SCFG Src-Pvt, Pvt-Trg Pvt X s, p, X p, t X s, t (17) (20) X s, p, X p, t X s, t, p (23) (17) (20) Trg Pvt ϕ ( t, p s ) ϕ ( s p, t ) ϕ ( t, p s ) = ϕ ( t p ) ϕ (p s) (24) ϕ ( s p, t ) = ϕ (s p) (25) Src-Pvt ϕ (p s) ϕ (s p) ϕ lex (p s) ϕ lex (s p) T SP 10 ϕ ( t s ) ϕ ( s t ) ϕ (p s) ϕ (s p) ( ) ( ) ϕ lex t s ϕlex s t ϕlex (p s) ϕ lex (s p) ϕ ( t, p s ) ϕ ( s p, t ) t p MSCFG 5.4 s, t s, t, p Neubig T 1 T 2 T 1 - (Neubig et al. 2015) T 1 = T rg T 2 = P vt s T rg ϕ ( t s ) L t t ϕ ( t, p s ) p 517
20 Vol. 23 No. 5 December (En) (Ar) (Es) (Fr) (Ru) (Zh) 5 Src-Pvt (train1) 10 Pvt-Trg (train2) 10 (test) (dev) 1, train1+train SCFG MSCFG Travatar (Neubig 2013) Hiero SCFG BLEU (Papineni et al. 2002) MERT (Och 2003) BLEU MSCFG L = 20 T 1-6 Cascade Src-Pvt Pvt-Trg SCFG 3.1 w/ PvtLM 200k/5M Src-Pvt Tri. SCFG SCFG Src-Pvt Pvt-Trg SCFG Src-Trg SCFG 3.3 Tri. MSCFG MSCFG Src-Pvt Pvt-Trg SCFG Src-Trg-Pvt MSCFG 5 w/o PvtLM w/ PvtLM 200k/5M
21 Neubig Sakti, (Koehn 2004) Tri. SCFG BLEU Tri. SCFG ( : p < 0.05, : p < 0.01) BLEU BLEU MSCFG (Tri. MSCFG w/o PvtLM) 2 Src Ar Es Fr Ru Zh Trg Cascade w/ PvtLM 200k Cascade w/ PvtLM 5M BLEU Score (%) Tri. SCFG (baseline) Tri. MSCFG w/o PvtLM Tri. MSCFG w/ PvtLM 200k Tri. MSCFG w/ PvtLM 5M Es Fr Ru Zh Ar Fr Ru Zh Ar Es Ru Zh Ar Es Fr Zh Ar Es Fr Ru
22 Vol. 23 No. 5 December 2016 SCFG 500 (Cascade w/ PvtLM 5M). Cascade w/ PvtLM 5M 20 (Cascade w/ PvtLM 200k) Zh-Ar Zh-Ru Tri. SCFG Tri. MSCFG w/ PvtLM 5M Cascade w/ PvtLM 5M
23 Neubig Sakti, (Brants, Popat, Xu, Och, and Dean 2007) Le nom du candidat proposé est indiqué dans l annexa à la présente note. El nombre del candidato propuesto se presenta en el anexo de la presente nota. The name of the candidate thus nominated is set out in the annex to the present note. Tri. SCFG: El nombre del proyecto de un candidato se indica en el anexo a la presente nota. (BLEU+1: 34.99) Tri. MSCFG w/ PvtLM 5M: El nombre del candidato propuesto se indica en el anexo a la presente nota. (BLEU+1: 61.13) The name of the candidate proposed indicated in the annex to the present note. proposé propuesto proyecto proposé propuesto proposed J. Risques d aspiration : citère de viscosité pour la classification des mélanges ; J. Peligros por aspiración : criterio de viscosidad para la clasificación de mezclas ; J. Aspiration hazards : viscosity criterion for classification of mixtures ; 521
24 Vol. 23 No. 5 December 2016 Direct 1: J. Riesgos d aspiration : criterio de viscosité para la clasificación de los mélanges ; (BLEU+1: 34.20) Direct 2: J. Riesgos d aspiration : criterio de viscosité para la clasificación de mezclas ; (BLEU+1: 49.16) Tri. MSCFG w/ PvtLM 2M: J. Riesgos d aspiration : viscosité criterios para la clasificación de mélanges ; (BLEU+1: 27.61) J. Risk d aspiration : viscosité criteria for the categorization of mélanges ; d aspiration mélanges d aspiration train1 train2 Direct 1 / 2 mélanges train2 Direct 1 2 criterio criterios 6.5 Europarl 4.4 Europarl Tri. SCFG Cascade Stanford POS Tagger (Toutanova and Manning 2000; Toutanova, Klein, Manning, and Singer 2003) F 522
25 Neubig Sakti, 3 4 F 3 F F Direct F Direct Direct F 3 Direct F-Measure (%) Tri. MSCFG w/ PvtLM 2M Tri.SCFG NC 8, (+0.01) P 6, (+1.02) DET 5, (+1.50) PUNC 4, (+0.44) ADJ 3, (+0.67) V 3, (+1.06) ADV 2, (+0.34) Direct F-Measure (%) Tri. MSCFG w/ PvtLM 2M Tri.SCFG NN 10, (+0.53) ART 4, (+1.24) CARD 3, ( 0.44) APPR 2, (+1.50) ADJA 2, (+0.47) NE 2, (+0.47) ADV 1, (+0.18) PPEF 1, (+1.67)
26 Vol. 23 No. 5 December F Direct 7 PBMT SCFG 6 524
27 Neubig Sakti, 1 SCFG 2 JSPS 16H ATR-Trek Brants, T., Popat, A. C., Xu, P., Och, F. J., and Dean, J. (2007). Large Language Models in Machine Translation. In Proceedings EMNLP, pp
28 Vol. 23 No. 5 December 2016 Brown, P. F., Pietra, V. J., Pietra, S. A. D., and Mercer, R. L. (1993). The Mathematics of Statistical Machine Translation: Parameter Estimation. Computational Linguistics, 19, pp Chappelier, J.-C. and Rajman, M. (1998). A Generalized CYK Algorithm for Parsing Stochastic CFG. In Proceedings TAPD, Vol. 98, No. 5, pp Chiang, D. (2007). Hierarchical Phrase-based Translation. Computational Linguistics, 33 (2), pp Cohn, T. and Lapata, M. (2007). Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora. In Proceedings ACL, pp Dabre, R., Cromieres, F., Kurohashi, S., and Bhattacharyya, P. (2015). Leveraging Small Multilingual Corpora for SMT Using Many Pivot Languages. In Proceedings NAACL, pp de Gispert, A. and Mariño, J. B. (2006). Catalan-English Statistical Machine Translation without Parallel Corpus: Bridging through Spanish. In Proceedings of LREC 5th Workshop on Strategies for Developing Machine Translation for Minority Languages, pp Dyer, C., Cordova, A., Mont, A., and Lin, J. (2008). Fast, Easy, and Cheap: Construction of Statistical Machine Translation Models with MapReduce. In Proceedings WMT, pp Goto, I., Utiyama, M., Sumita, E., Tamura, A., and Kurohashi, S. (2013). Distortion Model Considering Rich Context for Statistical Machine Translation. In Proceedings ACL, pp Heafield, K. (2011). KenLM: Faster and Smaller Language Model Queries. In Proceedings, WMT, pp Koehn, P. (2004). Statistical Significance Tests for Machine Translation Evaluation. In Lin, D. and Wu, D. (Eds.), Proceedings EMNLP, pp Koehn, P. (2005). Europarl: A Parallel Corpus for Statistical Machine Translation. In MT Summit, Vol. 5, pp Koehn, P., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., Bertoldi, N., Cowan, B., Shen, W., Moran, C., Zens, R., Dyer, C., Bojar, O., Constantin, A., and Herbst, E. (2007). Moses: Open Source Toolkit for Statistical Machine Translation. In Proceedings ACL, pp Koehn, P., Och, F. J., and Marcu, D. (2003). Statistical Phrase-Based Translation. In Proceedings NAACL, pp Levinboim, T. and Chiang, D. (2015). Supervised Phrase Table Triangulation with Neural Word Embeddings for Low-Resource Languages. In Proceedings EMNLP, pp Neubig Graham Sakti Sakriani (2014) (SIG-NL), 526
29 Neubig Sakti, 20, pp Neubig Graham Sakti Sakriani (2015) (SIG-NL), 2, pp Miura, A., Neubig, G., Sakti, S., Toda, T., and Nakamura, S. (2015). Improving Pivot Translation by Remembering the Pivot. In Proceedings ACL, pp Neubig, G. (2013). Travatar: A Forest-to-String Machine Translation Engine based on Tree Transducers. In Proceedings ACL Demo Track, pp Neubig, G., Arthur, P., and Duh, K. (2015). Multi-Target Machine Translation with Multi- Synchronous Context-free Grammars. In Proceedings NAACL, pp Neubig, G., Nakata, Y., and Mori, S. (2011). Pointwise Prediction for Robust, Adaptable Japanese Morphological Analysis. In Proceedings ACL, pp Nirenburg, S. (1989). Knowledge-Based Machine Translation. Machine Translation, 4 (1), pp Och, F. J. (2003). Minimum Error Rate Training in Statistical Machine Translation. In Proceedings ACL, pp Papineni, K., Roukos, S., Ward, T., and Zhu, W.-J. (2002). BLEU: A Method for Automatic Evaluation of Machine Translation. In Proceedings ACL, pp Shannon, C. E. (1948). A Mathematical Theory of Communication. Bell System Technical Journal, 27 (3), pp Toutanova, K., Klein, D., Manning, C. D., and Singer, Y. (2003). Feature-rich Part-of-speech Tagging with a Cyclic Dependency Network. In Proceedings NAACL, pp Toutanova, K. and Manning, C. D. (2000). Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger. In Proceedings EMNLP, pp Utiyama, M. and Isahara, H. (2007). A Comparison of Pivot Methods for Phrase-Based Statistical Machine Translation. In Proceedings NAACL, pp Zhu, X., He, Z., Wu, H., Zhu, C., Wang, H., and Zhao, T. (2014). Improving Pivot-Based Statistical Machine Translation by Pivoting the Co-occurrence Count of Phrase Pairs. In Proceedings EMNLP, pp Ziemski, M., Junczys-Dowmunt, M., and Pouliquen, B. (2016). The United Nations Parallel Corpus v1.0. In Proceedings LREC, pp
30 Vol. 23 No. 5 December ACL Graham Neubig: Sakriani Sakti: ATR INRIA JNS SFN ASJ ISCA IEICE IEEE PD IEEE ATR 2006 ATR Antonio Zampoli ISCA IEEE SLTC IEEE
Vol. 23 No. 5 December (Rule-Based Machine Translation; RBMT (Nirenburg 1989)) 2 (Statistical Machine Translation; SMT (Brown, Pietra, Piet
Graham Neubig, Sakriani Sakti 2,,,,, Improving Pivot Translation by Remembering the Pivot Akiva Miura, Graham Neubig,, Sakriani Sakti, Tomoki Toda and Satoshi Nakamura In statistical machine translation,
f ê ê = arg max Pr(e f) (1) e M = arg max λ m h m (e, f) (2) e m=1 h m (e, f) λ m λ m BLEU [11] [12] PBMT 2 [13][14] 2.2 PBMT Hiero[9] Chiang PBMT [X
![f ê ê = arg max Pr(e f) (1) e M = arg max λ m h m (e, f) (2) e m=1 h m (e, f) λ m λ m BLEU [11] [12] PBMT 2 [13][14] 2.2 PBMT Hiero[9] Chiang PBMT [X](/thumbs/76/74386625.jpg "f ê ê = arg max Pr(e f) (1) e M = arg max λ m h m (e, f) (2) e m=1 h m (e, f) λ m λ m BLEU [11] [12] PBMT 2 [13][14] 2.2 PBMT Hiero[9] Chiang PBMT [X")
1,a) Graham Neubig 1,b) Sakriani Sakti 1,c) 1,d) 1,e) 1. Statistical Machine Translation: SMT[1] [2] [3][4][5][6] 2 Cascade Translation [3] Triangulation [7] Phrase-Based Machine Translation: PBMT[8] 1
IPSJ SIG Technical Report Vol.2014-NL-219 No /12/17 1,a) Graham Neubig 1,b) Sakriani Sakti 1,c) 1,d) 1,e) 1. [23] 1(a) 1(b) [19] n-best [1] 1 N
![IPSJ SIG Technical Report Vol.2014-NL-219 No /12/17 1,a) Graham Neubig 1,b) Sakriani Sakti 1,c) 1,d) 1,e) 1. [23] 1(a) 1(b) [19] n-best [1] 1 N](/thumbs/103/160831289.jpg "IPSJ SIG Technical Report Vol.2014-NL-219 No /12/17 1,a) Graham Neubig 1,b) Sakriani Sakti 1,c) 1,d) 1,e) 1. [23] 1(a) 1(b) [19] n-best [1] 1 N")
1,a) Graham Neubig 1,b) Sakriani Sakti 1,c) 1,d) 1,e) 1. [23] 1(a) 1(b) [19] n-best [1] 1 Nara Institute of Science and Technology a) akabe.koichi.zx8@is.naist.jp b) neubig@is.naist.jp c) ssakti@is.naist.jp
2
NTT 2012 NTT Corporation. All rights reserved. 2 3 4 5 Noisy Channel f : (source), e : (target) ê = argmax e p(e f) = argmax e p(f e)p(e) 6 p( f e) (Brown+ 1990) f1 f2 f3 f4 f5 f6 f7 He is a high school
A Japanese Word Dependency Corpus ÆüËܸì¤Îñ¸ì·¸¤ê¼õ¤±¥³¡¼¥Ñ¥¹
A Japanese Word Dependency Corpus 2015 3 18 Special thanks to NTT CS, 1 /27 Bunsetsu? What is it? ( ) Cf. CoNLL Multilingual Dependency Parsing [Buchholz+ 2006] (, Penn Treebank [Marcus 93]) 2 /27 1. 2.
21 Pitman-Yor Pitman- Yor [7] n -gram W w n-gram G Pitman-Yor P Y (d, θ, G 0 ) (1) G P Y (d, θ, G 0 ) (1) Pitman-Yor d, θ, G 0 d 0 d 1 θ Pitman-Yor G
![21 Pitman-Yor Pitman- Yor [7] n -gram W w n-gram G Pitman-Yor P Y (d, θ, G 0 ) (1) G P Y (d, θ, G 0 ) (1) Pitman-Yor d, θ, G 0 d 0 d 1 θ Pitman-Yor G](/thumbs/89/99361107.jpg "21 Pitman-Yor Pitman- Yor [7] n -gram W w n-gram G Pitman-Yor P Y (d, θ, G 0 ) (1) G P Y (d, θ, G 0 ) (1) Pitman-Yor d, θ, G 0 d 0 d 1 θ Pitman-Yor G")
ol2013-nl-214 No6 1,a) 2,b) n-gram 1 M [1] (TG: Tree ubstitution Grammar) [2], [3] TG TG 1 2 a) ohno@ilabdoshishaacjp b) khatano@maildoshishaacjp [4], [5] [6] 2 Pitman-Yor 3 Pitman-Yor 1 21 Pitman-Yor
¥ì¥·¥Ô¤Î¸À¸ì½èÍý¤Î¸½¾õ
2013 8 18 Table of Contents = + 1. 2. 3. 4. 5. etc. 1. ( + + ( )) 2. :,,,,,, (MUC 1 ) 3. 4. (subj: person, i-obj: org. ) 1 Message Understanding Conference ( ) UGC 2 ( ) : : 2 User-Generated Content [
2014/1 Vol. J97 D No. 1 2 [2] [3] 1 (a) paper (a) (b) (c) 1 Fig. 1 Issues in coordinating translation services. (b) feast feast feast (c) Kran
![2014/1 Vol. J97 D No. 1 2 [2] [3] 1 (a) paper (a) (b) (c) 1 Fig. 1 Issues in coordinating translation services. (b) feast feast feast (c) Kran](/thumbs/92/107842917.jpg "2014/1 Vol. J97 D No. 1 2 [2] [3] 1 (a) paper (a) (b) (c) 1 Fig. 1 Issues in coordinating translation services. (b) feast feast feast (c) Kran")
a) b) c) Improving Quality of Pivot Translation by Context in Service Coordination Yohei MURAKAMI a), Rie TANAKA b),andtoruishida c) Web 1. Web 26.8% 30.9% 21.3% 21% 1 n n(n 1) Department of Social Informatics,
( ) Kevin Duh
NAIST-IS-MT1251045 Factored Translation Models 2014 2 6 ( ) Kevin Duh Factored Translation Models Factored translation models Factored Translation Models, NAIST-IS-MT1251045, 2014 2 6. i Post-ordering
IPSJ-TOD
Vol. 3 No. 2 91 101 (June 2010) 1 1 1 2 1 TSC2 Automatic Evaluation of Text Summaries by Using Paraphrase Kazuho Hirahara, 1 Hidetsugu Nanba, 1 Toshiyuki Takezawa 1 and Manabu Okumura 2 The evaluation
yasi10.dvi
2002 50 2 259 278 c 2002 1 2 2002 2 14 2002 6 17 73 PML 1. 1997 1998 Swiss Re 2001 Canabarro et al. 1998 2001 1 : 651 0073 1 5 1 IHD 3 2 110 0015 3 3 3 260 50 2 2002, 2. 1 1 2 10 1 1. 261 1. 3. 3.1 2 1
IPSJ SIG Technical Report Vol.2010-NL-199 No /11/ treebank ( ) KWIC /MeCab / Morphological and Dependency Structure Annotated Corp
1. 1 1 1 2 treebank ( ) KWIC /MeCab / Morphological and Dependency Structure Annotated Corpus Management Tool: ChaKi Yuji Matsumoto, 1 Masayuki Asahara, 1 Masakazu Iwatate 1 and Toshio Morita 2 This paper
Vol. 43 No. 7 July 2002 ATR-MATRIX,,, ATR ITL ATR-MATRIX ATR-MATRIX 90% ATR-MATRIX Development and Evaluation of ATR-MATRIX Speech Translation System
Vol. 43 No. 7 July 2002 ATR-MATRIX,,, ATR ITL ATR-MATRIX ATR-MATRIX 90% ATR-MATRIX Development and Evaluation of ATR-MATRIX Speech Translation System Fumiaki Sugaya,,, Toshiyuki Takezawa, Eiichiro Sumita,
gengo.dvi
4 97.52% tri-gram 92.76% 98.49% : Japanese word segmentation by Adaboost using the decision list as the weak learner Hiroyuki Shinnou In this paper, we propose the new method of Japanese word segmentation
ズテーブルを 用 いて 対 訳 専 門 用 語 を 獲 得 する 手 法 を 提 案 する 具 体 的 には まず 専 門 用 語 対 訳 辞 書 獲 得 の 情 報 源 として 用 いる 日 中 対 訳 文 対 に 対 して 句 に 基 づく 統 計 的 機 械 翻 訳 モデルを 適 用 すること
日 中 パテントファミリーを 利 用 した 専 門 用 語 訳 語 推 定 フレーズテーブルおよび 対 訳 文 対 を 利 用 する 方 式 Estimating Translation of Technical Terms utilizing Japanese-Chinese Patent Families : an Approach based on Phrase Translation Tables
自然言語処理22_289
(RNN) Dyer (Dyer, Clark, Lavie, and Smith 2011) IBM (Brown, Pietra, Pietra, and Mercer 1993) word embedding word embedding RNN (Yang, Liu, Li, Zhou, and Yu 2013) IBM 4 Recurrent Neural Networks for Word
x i 2 x x i i 1 i xi+ 1xi+ 2x i+ 3 健康児に本剤を接種し ( 窓幅 3 n-gram 長の上限 3 の場合 ) 文字 ( 種 )1-gram: -3/ 児 (K) -2/ に (H) -1/ 本 (K) 1/ 剤 (K) 2/ を (H) 3/ 接 (K) 文字 (
1. 2 1 NEUBIG Graham 1 1 1 Improving Part-of-Speech Tagging by Combining Pointwise and Sequence-based Predictors Yosuke NAKATA, 1 Graham NEUBIG, 1 Shinsuke MORI 1 and Tatsuya KAWAHARA 1 This paper proposes
一般社団法人電子情報通信学会 THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGIN
一般社団法人電子情報通信学会 THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS 信学技報 IEICE Technical Report SP2019-12(2019-08)
1 7.35% 74.0% linefeed point c 200 Information Processing Society of Japan
1 2 3 Incremental Linefeed Insertion into Lecture Transcription for Automatic Captioning Masaki Murata, 1 Tomohiro Ohno 2 and Shigeki Matsubara 3 The development of a captioning system that supports the
Modal Phrase MP because but 2 IP Inflection Phrase IP as long as if IP 3 VP Verb Phrase VP while before [ MP MP [ IP IP [ VP VP ]]] [ MP [ IP [ VP ]]]
![Modal Phrase MP because but 2 IP Inflection Phrase IP as long as if IP 3 VP Verb Phrase VP while before [ MP MP [ IP IP [ VP VP ]]] [ MP [ IP [ VP ]]]](/thumbs/89/98876548.jpg "Modal Phrase MP because but 2 IP Inflection Phrase IP as long as if IP 3 VP Verb Phrase VP while before [ MP MP [ IP IP [ VP VP ]]] [ MP [ IP [ VP ]]]")
30 4 2016 3 pp.195-209. 2014 N=23 (S)AdvOV (S)OAdvV 2 N=17 (S)OAdvV 2014 3, 2008 Koizumi 1993 3 MP IP VP 1 MP 2006 2002 195 Modal Phrase MP because but 2 IP Inflection Phrase IP as long as if IP 3 VP Verb
Computational Semantics 1 category specificity Warrington (1975); Warrington & Shallice (1979, 1984) 2 basic level superiority 3 super-ordinate catego
Computational Semantics 1 category specificity Warrington (1975); Warrington & Shallice (1979, 1984) 2 basic level superiority 3 super-ordinate category preservation 1 / 13 analogy by vector space Figure
EQUIVALENT TRANSFORMATION TECHNIQUE FOR ISLANDING DETECTION METHODS OF SYNCHRONOUS GENERATOR -REACTIVE POWER PERTURBATION METHODS USING AVR OR SVC- Ju
EQUIVALENT TRANSFORMATION TECHNIQUE FOR ISLANDING DETECTION METHODS OF SYNCHRONOUS GENERATOR -REACTIVE POWER PERTURBATION METHODS USING AVR OR SVC- Jun Motohashi, Member, Takashi Ichinose, Member (Tokyo
46 583/4 2012
4-3 A Transliteration System Based on Bayesian Alignment and its Human Evaluation within a Machine Translation System Andrew Finch and YASUDA Keiji This paper reports on contributions in two areas. Firstly,
IPSJ SIG Technical Report Vol.2017-SLP-115 No /2/18 1,a) 1 1,2 Sakriani Sakti [1][2] [3][4] [5][6][7] [8] [9] 1 Nara Institute of Scie
![IPSJ SIG Technical Report Vol.2017-SLP-115 No /2/18 1,a) 1 1,2 Sakriani Sakti [1][2] [3][4] [5][6][7] [8] [9] 1 Nara Institute of Scie](/thumbs/104/162724895.jpg "IPSJ SIG Technical Report Vol.2017-SLP-115 No /2/18 1,a) 1 1,2 Sakriani Sakti [1][2] [3][4] [5][6][7] [8] [9] 1 Nara Institute of Scie")
1,a) 1 1,2 Sakriani Sakti 1 1 1 1. [1][2] [3][4] [5][6][7] [8] [9] 1 Nara Institute of Science and Technology 2 Japan Science and Technology Agency a) ishikawa.yoko.io5@is.naist.jp 2. 1 Belief-Desire theory
johnny-paper2nd.dvi
13 The Rational Trading by Using Economic Fundamentals AOSHIMA Kentaro 14 2 26 ( ) : : : The Rational Trading by Using Economic Fundamentals AOSHIMA Kentaro abstract: Recently Artificial Markets on which
[1] B =b 1 b n P (S B) S S O = {o 1,2, o 1,3,, o 1,n, o 2,3,, o i,j,, o n 1,n } D = {d 1, d 2,, d n 1 } S = O, D o i,j 1 i
![[1] B =b 1 b n P (S B) S S O = {o 1,2, o 1,3,, o 1,n, o 2,3,, o i,j,, o n 1,n } D = {d 1, d 2,, d n 1 } S = O, D o i,j 1 i](/thumbs/79/79671767.jpg "[1] B =b 1 b n P (S B) S S O = {o 1,2, o 1,3,, o 1,n, o 2,3,, o i,j,, o n 1,n } D = {d 1, d 2,, d n 1 } S = O, D o i,j 1 i")
1,a) 2,b) 3,c) 1,d) CYK 552 1. 2 ( 1 ) ( 2 ) 1 [1] 2 [2] [3] 1 Graduate School of Information Science, Nagoya University, Japan 2 Information Technology Center, Nagoya University, Japan 3 Information &
BLEU Kishore Papineni, Salim Roukos, Todd Ward and Wei-Jing Zhu. (2002) BLEU: a method for Automatic Evaluation of Machine Translation. ACL. MT ( ) MT
4. BLEU @NICT mutiyama@nict.go.jp 1 BLEU Kishore Papineni, Salim Roukos, Todd Ward and Wei-Jing Zhu. (2002) BLEU: a method for Automatic Evaluation of Machine Translation. ACL. MT ( ) MT ( ) BLEU 2 BLEU
IBM-Mode1 Q: A: cash money It is fine today 2
8. IBM Model-1 @NICT mutiyama@nict.go.jp 1 IBM-Mode1 Q: A: cash money It is fine today 2 e f a P (f, a e) â : â = arg max a P (f, a e) â P (f, a e) 3 θ P (f e, θ) θ f d = { f, e } L(θ d) = log f,e d P
130 Oct Radial Basis Function RBF Efficient Market Hypothesis Fama ) 4) 1 Fig. 1 Utility function. 2 Fig. 2 Value function. (1) (2)
Vol. 47 No. SIG 14(TOM 15) Oct. 2006 RBF 2 Effect of Stock Investor Agent According to Framing Effect to Stock Exchange in Artificial Stock Market Zhai Fei, Shen Kan, Yusuke Namikawa and Eisuke Kita Several
..,,,, , ( ) 3.,., 3.,., 500, 233.,, 3,,.,, i
25 Feature Selection for Prediction of Stock Price Time Series 1140357 2014 2 28 ..,,,,. 2013 1 1 12 31, ( ) 3.,., 3.,., 500, 233.,, 3,,.,, i Abstract Feature Selection for Prediction of Stock Price Time
The Japanese Journal of Health Psychology, 29(S): (2017)
Journal of Health Psychology Research 2017, Vol. 29, Special issue, 139 149Journal of Health Psychology Research 2016, J-STAGE Vol. Advance 29, Special publication issue, 139 149 date : 5 December, 2016
Vol.54 No (July 2013) [9] [10] [11] [12], [13] 1 Fig. 1 Flowchart of the proposed system. c 2013 Information
![Vol.54 No (July 2013) [9] [10] [11] [12], [13] 1 Fig. 1 Flowchart of the proposed system. c 2013 Information](/thumbs/91/104959916.jpg "Vol.54 No (July 2013) [9] [10] [11] [12], [13] 1 Fig. 1 Flowchart of the proposed system. c 2013 Information")
Vol.54 No.7 1937 1950 (July 2013) 1,a) 2012 11 1, 2013 4 5 1 Similar Sounds Sentences Generator Based on Morphological Analysis Manner and Low Class Words Masaaki Kanakubo 1,a) Received: November 1, 2012,
THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE.
THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE. E-mail: {ytamura,takai,tkato,tm}@vision.kuee.kyoto-u.ac.jp Abstract Current Wave Pattern Analysis for Anomaly
IPSJ SIG Technical Report Vol.2009-BIO-17 No /5/26 DNA 1 1 DNA DNA DNA DNA Correcting read errors on DNA sequences determined by Pyrosequencing
DNA 1 1 DNA DNA DNA DNA Correcting read errors on DNA sequences determined by Pyrosequencing Youhei Namiki 1 and Yutaka Akiyama 1 Pyrosequencing, one of the DNA sequencing technologies, allows us to determine
main.dvi
305 8550 1 2 CREST fujii@slis.tsukuba.ac.jp 1 7% 2 2 3 PRIME Multi-lingual Information Retrieval 2 2.1 Cross-Language Information Retrieval CLIR 1990 CD-ROM a. b. c. d. b CLIR b 70% CLIR CLIR 2.2 (b) 2
1., 1 COOKPAD 2, Web.,,,,,,.,, [1]., 5.,, [2].,,.,.,, 5, [3].,,,.,, [4], 33,.,,.,,.. 2.,, 3.., 4., 5., ,. 1.,,., 2.,. 1,,
![1., 1 COOKPAD 2, Web.,,,,,,.,, [1]., 5.,, [2].,,.,.,, 5, [3].,,,.,, [4], 33,.,,.,,.. 2.,, 3.., 4., 5., ,. 1.,,., 2.,. 1,,](/thumbs/50/25936361.jpg "1., 1 COOKPAD 2, Web.,,,,,,.,, [1]., 5.,, [2].,,.,.,, 5, [3].,,,.,, [4], 33,.,,.,,.. 2.,, 3.., 4., 5., ,. 1.,,., 2.,. 1,,")
THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE.,, 464 8601 470 0393 101 464 8601 E-mail: matsunagah@murase.m.is.nagoya-u.ac.jp, {ide,murase,hirayama}@is.nagoya-u.ac.jp,
3807 (3)(2) ,267 1 Fig. 1 Advertisement to the author of a blog. 3 (1) (2) (3) (2) (1) TV 2-0 Adsense (2) Web ) 6) 3
Vol. 52 No. 12 3806 3816 (Dec. 2011) 1 1 Discovering Latent Solutions from Expressions of Dissatisfaction in Blogs Toshiyuki Sakai 1 and Ko Fujimura 1 This paper aims to find the techniques or goods that
% 95% 2002, 2004, Dunkel 1986, p.100 1
Blended Learning 要 旨 / Moodle Blended Learning Moodle キーワード:Blended Learning Moodle 1 2008 Moodle e Blended Learning 2009.. 1994 2005 1 2 93% 95% 2002, 2004, 2011 2011 1 Dunkel 1986, p.100 1 Blended Learning
fiš„v8.dvi
(2001) 49 2 333 343 Java Jasp 1 2 3 4 2001 4 13 2001 9 17 Java Jasp (JAva based Statistical Processor) Jasp Jasp. Java. 1. Jasp CPU 1 106 8569 4 6 7; fuji@ism.ac.jp 2 106 8569 4 6 7; nakanoj@ism.ac.jp
258 5) GPS 1 GPS 6) GPS DP 7) 8) 10) GPS GPS 2 3 4 5 2. 2.1 3 1) GPS Global Positioning System
Vol. 52 No. 1 257 268 (Jan. 2011) 1 2, 1 1 measurement. In this paper, a dynamic road map making system is proposed. The proposition system uses probe-cars which has an in-vehicle camera and a GPS receiver.
Hansen 1 2, Skinner 5, Augustinus 6, Harvey 7 Windle 8 Pels 9 1 Skinner 5 Augustinus 6 Pels 9 NL Harvey ML 11 NL
HANAOKA, Shinya 1 3 Hansen1, 2 1 2 3 Hansen 2 3 4 5 2 2.1 002 Vol.5 No.4 2003 Winter 3 4 2.2 Hansen 1 2, Skinner 5, Augustinus 6, Harvey 7 Windle 8 Pels 9 1 Skinner 5 Augustinus 6 Pels 9 NL Harvey 10 2.3
1 Web [2] Web [3] [4] [5], [6] [7] [8] S.W. [9] 3. MeetingShelf Web MeetingShelf MeetingShelf (1) (2) (3) (4) (5) Web MeetingShelf
![1 Web [2] Web [3] [4] [5], [6] [7] [8] S.W. [9] 3. MeetingShelf Web MeetingShelf MeetingShelf (1) (2) (3) (4) (5) Web MeetingShelf](/thumbs/79/80104027.jpg "1 Web [2] Web [3] [4] [5], [6] [7] [8] S.W. [9] 3. MeetingShelf Web MeetingShelf MeetingShelf (1) (2) (3) (4) (5) Web MeetingShelf")
1,a) 2,b) 4,c) 3,d) 4,e) Web A Review Supporting System for Whiteboard Logging Movies Based on Notes Timeline Taniguchi Yoshihide 1,a) Horiguchi Satoshi 2,b) Inoue Akifumi 4,c) Igaki Hiroshi 3,d) Hoshi
jpaper : 2017/4/17(17:52),,.,,,.,.,.,, Improvement in Domain Specific Word Segmentation by Symbol Grounding suzushi tomori, hirotaka kameko, takashi n
,,.,,,.,.,.,, Improvement in Domain Specific Word Segmentation by Symbol Grounding suzushi tomori, hirotaka kameko, takashi ninomiya, shinsuke mori and yoshimasa tsuruoka We propose a novel framework for
DEIM Forum 2009 E
DEIM Forum 2009 E5-3 464-8601 1 606-8501 464 8601 1 E-mail: lifushi@arch.itc.nagoya-u.ac.jp, mayumi@mm.media.kyoto-u.ac.jp, {hirano,kajita,mase}@itc.nagoya-u.ac.jp Abstract Study on a Recipe Recommendation
Vol. 48 No. 3 Mar PM PM PMBOK PM PM PM PM PM A Proposal and Its Demonstration of Developing System for Project Managers through University-Indus
Vol. 48 No. 3 Mar. 2007 PM PM PMBOK PM PM PM PM PM A Proposal and Its Demonstration of Developing System for Project Managers through University-Industry Collaboration Yoshiaki Matsuzawa and Hajime Ohiwa
& Vol.5 No (Oct. 2015) TV 1,2,a) , Augmented TV TV AR Augmented Reality 3DCG TV Estimation of TV Screen Position and Ro
TV 1,2,a) 1 2 2015 1 26, 2015 5 21 Augmented TV TV AR Augmented Reality 3DCG TV Estimation of TV Screen Position and Rotation Using Mobile Device Hiroyuki Kawakita 1,2,a) Toshio Nakagawa 1 Makoto Sato
[1], B0TB2053, 20014 3 31. i
![[1], B0TB2053, 20014 3 31. i](/thumbs/40/20550507.jpg "[1], B0TB2053, 20014 3 31. i")
B0TB2053 20014 3 31 [1], B0TB2053, 20014 3 31. i 1 1 2 3 2.1........................ 3 2.2........................... 3 2.3............................. 4 2.3.1..................... 4 2.3.2....................
IPSJ SIG Technical Report Vol.2011-EC-19 No /3/ ,.,., Peg-Scope Viewer,,.,,,,. Utilization of Watching Logs for Support of Multi-
1 3 5 4 1 2 1,.,., Peg-Scope Viewer,,.,,,,. Utilization of Watching Logs for Support of Multi-View Video Contents Kosuke Niwa, 1 Shogo Tokai, 3 Tetsuya Kawamoto, 5 Toshiaki Fujii, 4 Marutani Takafumi,
IPSJ SIG Technical Report Vol.2010-CVIM-170 No /1/ Visual Recognition of Wire Harnesses for Automated Wiring Masaki Yoneda, 1 Ta
1 1 1 1 2 1. Visual Recognition of Wire Harnesses for Automated Wiring Masaki Yoneda, 1 Takayuki Okatani 1 and Koichiro Deguchi 1 This paper presents a method for recognizing the pose of a wire harness
IIC Proposal of Range Extension Control System by Drive and Regeneration Distribution Based on Efficiency Characteristic of Motors for Electric
IIC-1-19 Proposal of Range Extension Control System by Drive and Regeneration Distribution Based on Efficiency Characteristic of Motors for Electric Vehicle Toru Suzuki, Hiroshi Fujimoto (Yokohama National
Rapp BLEU[10] [9] BLEU OrthoBLEU Rapp OrthoBLEU [9] OrthoBLEU OrthoBLEU ) ) ) 1) NTT Natural Language Research
![Rapp BLEU[10] [9] BLEU OrthoBLEU Rapp OrthoBLEU [9] OrthoBLEU OrthoBLEU ) ) ) 1) NTT Natural Language Research](/thumbs/54/33422724.jpg "Rapp BLEU[10] [9] BLEU OrthoBLEU Rapp OrthoBLEU [9] OrthoBLEU OrthoBLEU ) ) ) 1) NTT Natural Language Research")
RJ-008 Is Back Translation Really Unuseful? Validation of Back Translation from the Perspective of a Checking Method for Users Mai Miyabe Takashi Yoshino 1. [1, 2] [3] [4] 1 2 2 [3,5,6,7] [8, 9] 1: 2 3
taro.watanabe at nict.go.jp
taro.watanabe at nict.go.jp https://sites.google.com/site/alaginmt2014/ ... I want to study about machine translation. I need to master machine translation. machine translation want to study. infobox infobox
( )
NAIST-IS-MT1051071 2012 3 16 ( ) Pustejovsky 2 2,,,,,,, NAIST-IS- MT1051071, 2012 3 16. i Automatic Acquisition of Qualia Structure of Generative Lexicon in Japanese Using Learning to Rank Takahiro Tsuneyoshi
i
21 Fault-Toleranted Authentication Data Distribution Protocol for Autonomous Distributed Networks 1125153 2010 3 2 i Abstract Fault-Toleranted Authentication Data Distribution Protocol for Autonomous Distributed
No. 3 Oct The person to the left of the stool carried the traffic-cone towards the trash-can. α α β α α β α α β α Track2 Track3 Track1 Track0 1
ACL2013 TACL 1 ACL2013 Grounded Language Learning from Video Described with Sentences (Yu and Siskind 2013) TACL Transactions of the Association for Computational Linguistics What Makes Writing Great?
IPSJ SIG Technical Report Vol.2012-MUS-96 No /8/10 MIDI Modeling Performance Indeterminacies for Polyphonic Midi Score Following and
MIDI 1 2 3 2 1 Modeling Performance Indeterminacies for Polyphonic Midi Score Following and Its Application to Automatic Accompaniment Nakamura Eita 1 Yamamoto Ryuichi 2 Saito Yasuyuki 3 Sako Shinji 2
アジア言語を中心とした機械翻訳の評価 第 1 回アジア翻訳ワークショップ概要 Evaluation of Machine Translation Focusing on Asian Languages Overview of the 1st Workshop on Asian Translation
アジア言語を中心とした機械翻訳の評価 第 1 回アジア翻訳ワークショップ概要 Evaluation of Machine Translation Focusing on Asian Languages Overview of the 1st Workshop on Asian Translation 国立研究開発法人科学技術振興機構 PROFILE 情報企画部研究員 国立研究開発法人情報通信研究機構
(MIRU2008) HOG Histograms of Oriented Gradients (HOG)
(MIRU2008) 2008 7 HOG - - E-mail: katsu0920@me.cs.scitec.kobe-u.ac.jp, {takigu,ariki}@kobe-u.ac.jp Histograms of Oriented Gradients (HOG) HOG Shape Contexts HOG 5.5 Histograms of Oriented Gradients D Human
4. C i k = 2 k-means C 1 i, C 2 i 5. C i x i p [ f(θ i ; x) = (2π) p 2 Vi 1 2 exp (x µ ] i) t V 1 i (x µ i ) 2 BIC BIC = 2 log L( ˆθ i ; x i C i ) + q
![4. C i k = 2 k-means C 1 i, C 2 i 5. C i x i p [ f(θ i ; x) = (2π) p 2 Vi 1 2 exp (x µ ] i) t V 1 i (x µ i ) 2 BIC BIC = 2 log L( ˆθ i ; x i C i ) + q](/thumbs/92/110416683.jpg "4. C i k = 2 k-means C 1 i, C 2 i 5. C i x i p [ f(θ i ; x) = (2π) p 2 Vi 1 2 exp (x µ ] i) t V 1 i (x µ i ) 2 BIC BIC = 2 log L( ˆθ i ; x i C i ) + q")
x-means 1 2 2 x-means, x-means k-means Bayesian Information Criterion BIC Watershed x-means Moving Object Extraction Using the Number of Clusters Determined by X-means Clustering Naoki Kubo, 1 Kousuke
A Feasibility Study of Direct-Mapping-Type Parallel Processing Method to Solve Linear Equations in Load Flow Calculations Hiroaki Inayoshi, Non-member
A Feasibility Study of Direct-Mapping-Type Parallel Processing Method to Solve Linear Equations in Load Flow Calculations Hiroaki Inayoshi, Non-member (University of Tsukuba), Yasuharu Ohsawa, Member (Kobe
Table 1. Reluctance equalization design. Fig. 2. Voltage vector of LSynRM. Fig. 4. Analytical model. Table 2. Specifications of analytical models. Fig
Mover Design and Performance Analysis of Linear Synchronous Reluctance Motor with Multi-flux Barrier Masayuki Sanada, Member, Mitsutoshi Asano, Student Member, Shigeo Morimoto, Member, Yoji Takeda, Member
A Study of Effective Application of CG Multimedia Contents for Help of Understandings of the Working Principles of the Internal Combustion Engine (The
A Study of Effective Application of CG Multimedia Contents for Help of Understandings of the Working Principles of the Internal Combustion Engine (The Learning Effects of the Animation and the e-learning
11_寄稿論文_李_再校.mcd
148 2011.4 1 4 Alderson 1996, Chapelle 2001, Huston 2002, Barker 2004, Rimmer 2006, Chodorow et al. 2010 He & Dai 2006 2 3 4 2 5 4 1. 2. 3. 1 2 (1) 3 90 (2) 80 1964 Brown 80 90 British National Corpus
Outline ACL 2017 ACL ACL 2017 Chairs/Presidents
ACL 2017, 2017/9/7 Outline ACL 2017 ACL ACL 2017 Chairs/Presidents ACL ACL he annual meeting of the Association for Computational Linguistics (Computational Linguistics) (Natural Language Processing) /
[4], [5] [6] [7] [7], [8] [9] 70 [3] 85 40% [10] Snowdon 50 [5] Kemper [3] 2.2 [11], [12], [13] [14] [15] [16]
![[4], [5] [6] [7] [7], [8] [9] 70 [3] 85 40% [10] Snowdon 50 [5] Kemper [3] 2.2 [11], [12], [13] [14] [15] [16]](/thumbs/93/113784833.jpg "[4], [5] [6] [7] [7], [8] [9] 70 [3] 85 40% [10] Snowdon 50 [5] Kemper [3] 2.2 [11], [12], [13] [14] [15] [16]")
1,a) 1 2 1 12 1 2Type Token 2 1 2 1. 2013 25.1% *1 2012 8 2010 II *2 *3 280 2025 323 65 9.3% *4 10 18 64 47.6 1 Center for the Promotion of Interdisciplinary Education and Research, Kyoto University 2
新製品開発プロジェクトの評価手法
CIRJE-J-60 2001 8 A note on new product project selection model: Empirical analysis in chemical industry Kenichi KuwashimaUniversity of Tokyo Junichi TomitaUniversity of Tokyo August, 2001 Abstract By
(i) 1 (ii) ,, 第 5 回音声ドキュメント処理ワークショップ講演論文集 (2011 年 3 月 7 日 ) 1) 1 2) Lamel 2) Roy 3) 4) w 1 w 2 w n 2 2-g
1 2 1 closed Automatic Detection of Edited Parts in Inexact Transcribed Corpora Using Alignment between Edited Transcription and Corresponding Utterance Kengo Ohta, 1 Masatoshi Tsuchiya 2 and Seiichi Nakagawa
Haiku Generation Based on Motif Images Using Deep Learning Koki Yoneda 1 Soichiro Yokoyama 2 Tomohisa Yamashita 2 Hidenori Kawamura Scho
Haiku Generation Based on Motif Images Using Deep Learning 1 2 2 2 Koki Yoneda 1 Soichiro Yokoyama 2 Tomohisa Yamashita 2 Hidenori Kawamura 2 1 1 School of Engineering Hokkaido University 2 2 Graduate
DSF-517.dvi
1 Example Based Dialogue System Based on Satisfaction Prediction Masahiro Mizukami Nara Institute of Science and Technology masahiro-mi@is.naist.jp Lasguido Nio lasguido.kp9@is.naist.jp Hideaki Kizuki
untitled
JAIS 1 2 1 2 In this paper, we focus on the pauses that partly characterize the utterances of simultaneous interpreters, and attempt to analyze the results of experiments conducted using human subjects
89-95.indd
解 説 機械翻訳最新事情 : ( 上 ) 統計的機械翻訳入門 永田昌明渡辺太郎塚田元 NTT 科学基礎研究所 統計的機械翻訳 (statistical machin translation) は, 互いに翻訳になっている 2 つの言語の文の対から翻訳規則や対訳辞書を自動的に学習し, 言語翻訳を実現する技術である. この技術は過去 0 年間に大きく進歩し, アラビア語と英語のような語順が比較的近い言語対では,
Q [4] 2. [3] [5] ϵ- Q Q CO CO [4] Q Q [1] i = X ln n i + C (1) n i i n n i i i n i = n X i i C exploration exploitation [4] Q Q Q ϵ 1 ϵ 3. [3] [5] [4]
![Q [4] 2. [3] [5] ϵ- Q Q CO CO [4] Q Q [1] i = X ln n i + C (1) n i i n n i i i n i = n X i i C exploration exploitation [4] Q Q Q ϵ 1 ϵ 3. [3] [5] [4]](/thumbs/93/112440494.jpg "Q [4] 2. [3] [5] ϵ- Q Q CO CO [4] Q Q [1] i = X ln n i + C (1) n i i n n i i i n i = n X i i C exploration exploitation [4] Q Q Q ϵ 1 ϵ 3. [3] [5] [4]")
1,a) 2,3,b) Q ϵ- 3 4 Q greedy 3 ϵ- 4 ϵ- Comparation of Methods for Choosing Actions in Werewolf Game Agents Tianhe Wang 1,a) Tomoyuki Kaneko 2,3,b) Abstract: Werewolf, also known as Mafia, is a kind of
A Study on Throw Simulation for Baseball Pitching Machine with Rollers and Its Optimization Shinobu SAKAI*5, Yuichiro KITAGAWA, Ryo KANAI and Juhachi
A Study on Throw Simulation for Baseball Pitching Machine with Rollers and Its Optimization Shinobu SAKAI*5, Yuichiro KITAGAWA, Ryo KANAI and Juhachi ODA Department of Human and Mechanical Systems Engineering,
IPSJ SIG Technical Report Vol.2015-MUS-107 No /5/23 HARK-Binaural Raspberry Pi 2 1,a) ( ) HARK 2 HARK-Binaural A/D Raspberry Pi 2 1.
HARK-Binaural Raspberry Pi 2 1,a) 1 1 1 2 3 () HARK 2 HARK-Binaural A/D Raspberry Pi 2 1. [1,2] [2 5] () HARK (Honda Research Institute Japan audition for robots with Kyoto University) *1 GUI ( 1) Python
,,,,., C Java,,.,,.,., ,,.,, i
24 Development of the programming s learning tool for children be derived from maze 1130353 2013 3 1 ,,,,., C Java,,.,,.,., 1 6 1 2.,,.,, i Abstract Development of the programming s learning tool for children
: ( 1) () 1. ( 1) 2. ( 1) 3. ( 2)
Acquiring Organized Information from News by Incremental Theme Refinements 1 1 1 Yutaro Taniguchi 1 Tetsunori Kobayashi 1 Yoshihiko Hayashi 1 1 1 School of Science and Engineering, Waseda University Abstract:
Vol. 9 No. 5 Oct. 2002 (?,?) 2000 6 5 6 2 3 6 4 5 2 A B C D 132
2000 6 5 6 :, Supporting Conference Program Production Using Natural Language Processing Technologies Hiromi itoh Ozaku Masao Utiyama Masaki Murata Kiyotaka Uchimoto and Hitoshi Isahara We applied natural
4.1 % 7.5 %
2018 (412837) 4.1 % 7.5 % Abstract Recently, various methods for improving computial performance have been proposed. One of these various methods is Multi-core. Multi-core can execute processes in parallel
Mimehand II[1] [2] 1 Suzuki [3] [3] [4] (1) (2) 1 [5] (3) 50 (4) 指文字, 3% (25 個 ) 漢字手話 + 指文字, 10% (80 個 ) 漢字手話, 43% (357 個 ) 地名 漢字手話 + 指文字, 21
![Mimehand II[1] [2] 1 Suzuki [3] [3] [4] (1) (2) 1 [5] (3) 50 (4) 指文字, 3% (25 個 ) 漢字手話 + 指文字, 10% (80 個 ) 漢字手話, 43% (357 個 ) 地名 漢字手話 + 指文字, 21](/thumbs/84/89593262.jpg "Mimehand II[1] [2] 1 Suzuki [3] [3] [4] (1) (2) 1 [5] (3) 50 (4) 指文字, 3% (25 個 ) 漢字手話 + 指文字, 10% (80 個 ) 漢字手話, 43% (357 個 ) 地名 漢字手話 + 指文字, 21")
1 1 1 1 1 1 1 2 transliteration Machine translation of proper names from Japanese to Japanese Sign Language Taro Miyazaki 1 Naoto Kato 1 Hiroyuki Kaneko 1 Seiki Inoue 1 Shuichi Umeda 1 Toshihiro Shimizu
自然言語処理24_705
nwjc2vec: word2vec nwjc2vec nwjc2vec nwjc2vec 2 nwjc2vec 7 nwjc2vec word2vec nwjc2vec: Word Embedding Data Constructed from NINJAL Web Japanese Corpus Hiroyuki Shinnou, Masayuki Asahara, Kanako Komiya
1 2 8 24 32 44 48 49 50 SEC journal Vol.11 No.2 Sep. 2015 1 2 SEC journal Vol.11 No.2 Sep. 2015 SEC journal Vol.11 No.2 Sep. 2015 3 4 SEC journal Vol.11 No.2 Sep. 2015 SEC journal Vol.11 No.2 Sep. 2015
10_08.dvi
476 67 10 2011 pp. 476 481 * 43.72.+q 1. MOS Mean Opinion Score ITU-T P.835 [1] [2] [3] Subjective and objective quality evaluation of noisereduced speech. Takeshi Yamada, Shoji Makino and Nobuhiko Kitawaki
1 (1997) (1997) 1974:Q3 1994:Q3 (i) (ii) ( ) ( ) 1 (iii) ( ( 1999 ) ( ) ( ) 1 ( ) ( 1995,pp ) 1
1 (1997) (1997) 1974:Q3 1994:Q3 (i) (ii) ( ) ( ) 1 (iii) ( ( 1999 ) ( ) ( ) 1 ( ) ( 1995,pp.218 223 ) 1 2 ) (i) (ii) / (iii) ( ) (i ii) 1 2 1 ( ) 3 ( ) 2, 3 Dunning(1979) ( ) 1 2 ( ) ( ) ( ) (,p.218) (
VRSJ-SIG-MR_okada_79dce8c8.pdf
THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE. 630-0192 8916-5 E-mail: {kaduya-o,takafumi-t,goshiro,uranishi,miyazaki,kato}@is.naist.jp,.,,.,,,.,,., CG.,,,
untitled
2009 57 2 393 411 c 2009 1 1 1 2009 1 15 7 21 7 22 1 1 1 1 1 1 1 1. 1 1 1 2 3 4 12 2000 147 31 1 3,941 596 1 528 1 372 1 1 1.42 350 1197 1 13 1 394 57 2 2009 1 1 19 2002 2005 4.8 1968 5 93SNA 6 12 1 7,
IPSJ SIG Technical Report Vol.2014-DBS-159 No.6 Vol.2014-IFAT-115 No /8/1 1,a) 1 1 1,, 1. ([1]) ([2], [3]) A B 1 ([4]) 1 Graduate School of Info
![IPSJ SIG Technical Report Vol.2014-DBS-159 No.6 Vol.2014-IFAT-115 No /8/1 1,a) 1 1 1,, 1. ([1]) ([2], [3]) A B 1 ([4]) 1 Graduate School of Info](/thumbs/101/149057081.jpg "IPSJ SIG Technical Report Vol.2014-DBS-159 No.6 Vol.2014-IFAT-115 No /8/1 1,a) 1 1 1,, 1. ([1]) ([2], [3]) A B 1 ([4]) 1 Graduate School of Info")
1,a) 1 1 1,, 1. ([1]) ([2], [3]) A B 1 ([4]) 1 Graduate School of Information Science and Technology, Osaka University a) kawasumi.ryo@ist.osaka-u.ac.jp 1 1 Bucket R*-tree[5] [4] 2 3 4 5 6 2. 2.1 2.2 2.3
Vol. 42 No MUC-6 6) 90% 2) MUC-6 MET-1 7),8) 7 90% 1 MUC IREX-NE 9) 10),11) 1) MUCMET 12) IREX-NE 13) ARPA 1987 MUC 1992 TREC IREX-N
Vol. 42 No. 6 June 2001 IREX-NE F 83.86 A Japanese Named Entity Extraction System Based on Building a Large-scale and High-quality Dictionary and Pattern-matching Rules Yoshikazu Takemoto, Toshikazu Fukushima
1 2 1 2012 39 1964 1997 1 p. 65 1 88 2 1 2 2 1 2 5 3 2 1 89 1 2012 Frantzen & Magnan 2005 2010 6 N2 2014 3 3.1 2015 2009 1 2 3 2 90 2 3 2 B1 B1 1 2 1 2 1 2 1 3.2 1 2014 2015 2 2 2014 2015 9 4.1 91 1 2
[1] [2] [3] 1 GPS 1 Twitter *1 *1 GPS [4] [5] [6] 2 [7] 1 [8] Restricted Boltzmann Machine RBM RBM
![[1] [2] [3] 1 GPS 1 Twitter *1 *1 GPS [4] [5] [6] 2 [7] 1 [8] Restricted Boltzmann Machine RBM RBM](/thumbs/88/115827067.jpg "[1] [2] [3] 1 GPS 1 Twitter *1 *1 GPS [4] [5] [6] 2 [7] 1 [8] Restricted Boltzmann Machine RBM RBM")
1,a) 2, 1,b) 1,c) 3,d) 1,e) 2014 2 21, 2014 9 12 2 Automatic Generation of Shogi Commentary with a Log-linear Language Model Hirotaka Kameko 1,a) Makoto Miwa 2, 1,b) Yoshimasa Tsuruoka 1,c) Shinsuke Mori
2 22006 2 e-learning e e 2003 1 4 e e e-learning 2 Web e-leaning 2004 2005 2006 e 4 GP 4 e-learning e-learning e-learning e LMS LMS Internet Navigware
2 2 Journal of Multimedia Aided Education Research 2006, Vol. 2, No. 2, 19 e 1 1 2 2 1 1 GP e 2004 e-learning 2004 e-learning 2005 e-learning e-learning e-learning e-learning 2004 e-learning HuWeb 2005
Stepwise Chow Test * Chow Test Chow Test Stepwise Chow Test Stepwise Chow Test Stepwise Chow Test Riddell Riddell first step second step sub-step Step
Stepwise Chow Test * Chow Test Chow Test Stepwise Chow Test Stepwise Chow Test Stepwise Chow Test Riddell Riddell first step second step sub-step Stepwise Chow Test a Stepwise Chow Test Takeuchi 1991Nomura
IPSJ SIG Technical Report Vol.2009-DPS-141 No.20 Vol.2009-GN-73 No.20 Vol.2009-EIP-46 No /11/27 1. MIERUKEN 1 2 MIERUKEN MIERUKEN MIERUKEN: Spe
1. MIERUKEN 1 2 MIERUKEN MIERUKEN MIERUKEN: Speech Visualization System Based on Augmented Reality Yuichiro Nagano 1 and Takashi Yoshino 2 As the spread of the Augmented Reality(AR) technology and service,
LAN LAN LAN LAN LAN LAN,, i
22 A secure wireless communication system using virtualization technologies 1115139 2011 3 4 LAN LAN LAN LAN LAN LAN,, i Abstract A secure wireless communication system using virtualization technologies
自然言語処理23_175
2 Sequence Alignment as a Set Partitioning Problem Masaaki Nishino,JunSuzuki, Shunji Umetani, Tsutomu Hirao and Masaaki Nagata Sequence alignment, which involves aligning elements of two given sequences,
Studies of Foot Form for Footwear Design (Part 9) : Characteristics of the Foot Form of Young and Elder Women Based on their Sizes of Ball Joint Girth
Studies of Foot Form for Footwear Design (Part 9) : Characteristics of the Foot Form of Young and Elder Women Based on their Sizes of Ball Joint Girth and Foot Breadth Akiko Yamamoto Fukuoka Women's University,
The 18th Game Programming Workshop ,a) 1,b) 1,c) 2,d) 1,e) 1,f) Adapting One-Player Mahjong Players to Four-Player Mahjong
1 4 1,a) 1,b) 1,c) 2,d) 1,e) 1,f) 4 1 1 4 1 4 4 1 4 Adapting One-Player Mahjong Players to Four-Player Mahjong by Recognizing Folding Situations Naoki Mizukami 1,a) Ryotaro Nakahari 1,b) Akira Ura 1,c)
知能と情報, Vol.30, No.5, pp
1, Adobe Illustrator Photoshop [1] [2] [3] Initital Values Assignment of Parameters Using Onomatopoieas for Interactive Design Tool Tsuyoshi NAKAMURA, Yuki SAWAMURA, Masayoshi KANOH, and Koji YAMADA Graduate
24312.dvi
Cognitive Studies, 24(3), 410-434. (Sep. 2017) The Table-talk Role Playing Game (TRPG) is an analog game. This game progresses by repeating acts of speech between a Game Master (GM) and a Player (PL).
[2] OCR [3], [4] [5] [6] [4], [7] [8], [9] 1 [10] Fig. 1 Current arrangement and size of ruby. 2 Fig. 2 Typography combined with printing
![[2] OCR [3], [4] [5] [6] [4], [7] [8], [9] 1 [10] Fig. 1 Current arrangement and size of ruby. 2 Fig. 2 Typography combined with printing](/thumbs/93/112070099.jpg "[2] OCR [3], [4] [5] [6] [4], [7] [8], [9] 1 [10] Fig. 1 Current arrangement and size of ruby. 2 Fig. 2 Typography combined with printing")
1,a) 1,b) 1,c) 2012 11 8 2012 12 18, 2013 1 27 WEB Ruby Removal Filters Using Genetic Programming for Early-modern Japanese Printed Books Taeka Awazu 1,a) Masami Takata 1,b) Kazuki Joe 1,c) Received: November
自然言語処理16_2_45
FileMaker Pro E-learning GUI Phrase Reading Cloze. E-learning Language Processing Technology and Educational Material Development Generating English Educational Material using a Database Software Kenichi