文献目録

1

Peter F. Brown, Stephen A. Della Pietra, Vincent J. Della Pietra, and Robert L. Mercer. "The machinematics of machine translation: Parameter estimation", Computational Linguistics, 19(2): pp. 263-311. (1993).

2

Philipp Koehn, Franz J. Och, and Daniel Marcu. " Statistical phrase-based translation". In Marti Hearst and Mari Ostendorf, editors, HLT-NAACL 2003: Main Proceedings, pages 127.133, Edmonton, Alberta, Canada, May 27 -June 1. Association for Computational Linguistics. (2003).

3

Pierre Isabelle, Cyril Goutte, and Michel Simard., ``Domain Adaptation of MT systems through automatic post-editing'', MT Summit XI, 102, 2007.

4

Philipp Koehn, Marcello Federico, Brooke Cowan, Richard Zens, Chris Dyer, Bojar, Alexandra Constantin, Evan Herbst, ``Moses: Open Source Toolkit for Statistical Machine Translation'', Proceedings of the ACL 2007 Demo and Poster Sessions, pages 177-180, 2007.

5

Yushi Xu and Stephanie Seneff, "Two-Stage Translation: A Combined Linguistic and Statistical Machine Translation Framework", Proceedings of the Eighth Conference of the Association for Machine Translation (AMTA) 2008.

6

Franz Josef Och, Hermann Ney, ``A Systematic Comparison of Various Statistical Alignment Models'', Computational Linguistics, volume 29, number 1, pp. 19-51, 2003.

7

Andreas Stolcke, ``SRILM - An Extensible Language Modeling Toolkit'', in Proc. Intl. Conf. Spoken Language Processing, Denver, Colorado, September 2002

8

K. Papineni, S. Roukos, T. Ward, W. J. Zhu, ``BLEU: a method for automatic evaluation of machine translation'', 40th Annual meeting of the Association for Computational Linguistics pp. 311-318, 2002.

9

Banerjee, S. and A. Lavie, ``METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments'', Proceedings of Workshop on Intrinsic and Extrinsic Evaluation Measures for MT and/or Summarization at the 43th Annual Meeting of the Association of Computational Linguistics (ACL-2005), June 2005.

10

Terumasa EHARA, ``Rule Based Machine Translation Combined with Statistical Post Editor for Japanese to English Patent Translation'', Proceedings of Machine Translation Summit XI, Workshop on Patent Translation, pp.13-18, Sept., 2007.

11

L.Dugast, J.Senellart, and P.Koehn, ``Statistical postediting on SYSTRAN's rule-based translation system'', in Second Workshop on SMT, 2007, pages.179-182

12

M.Simard, N.Ueffing, P.Isabelle, and R.Kuhn, ``Rule-based translation with statistical phrase-based post-editing'', in Second Workshop on SMT, 2007, pages.203-206

13

Zhifei Li, Chris Callison-Burch, Chris Dyer, Juri Ganitkevitch, Sanjeev Khudanpur, Lane Schwartz, Wren Thornton, Jonathan Weese and Omar Zaidan, ``Joshua: An Open Source Toolkit for Parsing-based Machine Translation'', In Proceedings of the Workshop on Statistical Machine Translation (WMT09), 2009.

表 12: Additional Experiments

IWSLT10
case+punc	BLEU	METEOR	WER	NIST
Proposed (=PBMT+MOSES)	0.5201	0.7916	0.3305	8.5812
MOSES	0.5077	0.7808	0.3365	8.4804
SYSTRAN+MOSES	0.5341	0.8001	0.3177	8.7090
JOSHUA	0.4871	0.7648	0.3443	8.0456
SYSTRAN+JOSHUA	0.5209	0.7892	0.3186	8.5260
MOSES(no tuning)	0.4882	0.7700	0.3655	8.3291
SYSTRAN+MOSES(no tuning)	0.5104	0.7909	0.3479	8.5575
PBMT+MOSES (no tuning)	0.4991	0.7797	0.3600	8.4342
no_case+no_punc	BLEU	METEOR	WER	NIST
Proposed (=PBMT+MOSES)	0.4949	0.7606	0.3776	8.7709
MOSES	0.4812	0.7488	0.3920	8.6752
SYSTRAN+MOSES	0.5110	0.7707	0.3655	8.9056
JOSHUA	0.4580	0.7292	0.4021	8.0676
SYSTRAN+JOSHUA	0.4977	0.7604	0.3682	8.6502
MOSES (no tuning)	0.4584	0.7351	0.4218	8.4744
SYSTRAN+MOSES(no tuning)	0.4815	0.7610	0.3990	8.7320
PBMT+MOSES (no tuning)	0.4711	0.7482	0.4110	8.6140
IWSLT09
case+punc	BLEU	METEOR	WER	NIST
Proposed (=PBMT+MOSES)	0.5894	0.8173	0.2932	9.2554
MOSES	0.5793	0.8079	0.3065	9.1049
SYSTRAN+MOSES	0.5985	0.8268	0.2814	9.3422
JOSHUA	0.5696	0.7940	0.3096	8.8269
SYSTRAN+JOSHUA	0.5850	0.8112	0.2923	9.0368
MOSES (no tuning)	0.5574	0.7940	0.3275	8.8250
SYSTRAN+MOSES (no tuning)	0.5809	0.8132	0.3071	9.1918
PBMT+MOSES (no tuning)	0.5670	0.8005	0.3235	9.0278
no_case+no_punc	BLEU	METEOR	WER	NIST
Proposed (=PBMT+MOSES)	0.5670	0.7844	0.3360	9.6467
MOSES	0.5504	0.7748	0.3541	9.4419
SYSTRAN+MOSES	0.5742	0.7965	0.3198	9.7262
JOSHUA	0.5438	0.7592	0.3587	9.1024
SYSTRAN+JOSHUA	0.5603	0.7805	0.3289	9.3301
MOSES(no tuning)	0.5301	0.7607	0.3784	9.1431
SYSTRAN+MOSES(no tuning)	0.5494	0.7830	0.3486	9.5210
PBMT+MOSES (no tuning)	0.5381	0.7678	0.3684	9.3586