_AAMT/Japio特許翻訳研究会.key

Size: px

Start display at page:

Download "_AAMT/Japio特許翻訳研究会.key"

ためひといそみ
5 years ago
Views:

1 2017/02/10 D2

2 ( ) ~ ~11 :

3 ( )!?

4 11 Google+

5 = = ( + )

6 (NMT) 1 ( ) Google (Wu et al., 2016) NMT news test 2013 BLEU score ( ) (:

7 : ht = f (ht-1, vt) (f) I saw a girl EOS EOS (Cho et al., 2014a; Sutskever et al., 2014)

8 I saw a girl EOS i j (i)h i EOS (Bahdanau et al., 2015; Luong et al., 2015b)

9 (Bahdanau et al., 2015)

10 NMT (Liu et al., 2006) NMT I saw a girl

11 - - I saw a girl

12 2 I saw a girl

13 : h p node = g 1 (h p left, h p right) I saw a girl

14 s1 = g 2 (hn, h p root) I saw a girl

15 N2 (N-1) : i1 j (i1)h i1 + i2 j (i2)h p i2 I saw a girl

16 I saw a girl

17 h p root s1 = g 2 (hn, h p root) I saw a girl

18 ASPEC (130) : 134, : 1789, : 1811 : (, ) = (87K, 65K) : Enju (Miyao and Tsujii, 2008) : {512, 768, 1024}, : : SGD BlackOut ( Softmax) (Ji et al, 2016) : + (: 20)

19 BLEU (Papieni et al., 2002), RIBES (Isozaki et al., 2010)

20 [ ] SiO2 films showed excellent performance even at 430 or less, and the memory effect of Si dot MOS capacitor was confirmed. [] SiO2 430 Si MOS [ ] SiO2 430 Si MOS

21 [] [ ] ( =0.77) ( =0.35) ( =0.31) ( =0.24) The liquid crystal for active matrix was injected into the cells.

22 ( ) 1 (Chung et al., 2016)

23 1 (Sennrich et al., 2016c) h p node = g 3 (h p left, h p right, xlabel) : S VP NP I saw a girl

24 ASPEC : 512, : : SGD Softmax : + (: 20)

26 1 [ ] The electric power generation was the 380 micro watt. [] [ ] UNKW [ ] ( = 0.78)

27 2 [ ] This paper describes development outline of low-loss forsterite porcelain. [] [ ] UNKUNK [ ]

28 sub-word ( ) > sub-word (Sennrich et al., 2016a) >> > sub-word > (Softmax) RNN NMT (Cho et al., 2014b) BLEU (Wu et al., 2016)

29 GitHub N3LP N3LP ( ( : ) C++, Eigen CPU +NLP ( publications/talk/pfi_dl2016/slides.pdf)

30 ( 15) (

31 NMT (Luong et al., 2015a) (Luong et al., 2016c) (Hashimoto et al., 2016) (Johnson et al., 2016) (Sennrich et al., 2016a) (Sennrich et al., 2016b) (Kim et al., 2017; Hashimoto and Tsuruoka, 2017) (Eriguchi et al., 2017)

32 : WAT 16 NMT : 5 (Cromieres et al., 2016) 2

33 () ( ) WMT 17 BLEU =

34 (Eriguchi et al., 2016a) (Eriguchi et al., 2016b)

35 (Bahdanau et al., 2015) Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio Neural Machine Translation by Jointly Learning to Align and Translate. In Proceedings of the 3rd International Conference on Learning Representations. (Chung et al., 2016) Junyoung Chung, Kyunghyun Cho, and Yoshua Bengio A character-level decoder without explicit segmentation for neural machine translation. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, pages (Cho et al., 2014a) Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio Learning Phrase Representations using RNN Encoder Decoder for Statistical Machine Translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages (Cho et al., 2014b) KyungHyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014a. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. In Proceedings of Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8). (Eriguchi et al., 2016a) Akiko Eriguchi, Kazuma Hashimoto, and Yoshimasa Tsuruoka Tree-tosequence attentional neural machine translation. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, pages (Eriguchi et al., 2016b) Akiko Eriguchi, Kazuma Hashimoto, and Yoshimasa Tsuruoka Characterbased Decoding in Tree-to-Sequence Attention-based Neural Machine Translation. In Proceedings of the 3rd Workshop on Asian Translation (WAT2016). The COLING 2016 Organizing Committee, pages (Eriguchi et al., 2017) Akiko Eriguchi, Yoshimasa Tsuruoka, and Kyunghyun Cho Learning to Parse and Translate Improves Neural Machine Translation. arxiv preprint arxiv:

36 (Hashimoto et al., 2016) Kazuma Hashimoto, Akiko Eriguchi, and Yoshimasa Tsuruoka Domain Adaptation and Attention-Based Unknown Word Replacement in Chinese-to-Japanese Neural Machine Translation. In Proceedings of the 3rd Workshop on Asian Translation (WAT2016). The COLING 2016 Organizing Committee, pages (Hashimoto et al., 2017) Kazuma Hashimoto and Yoshimasa Tsuruoka Neural Machine Translation with Source-Side Latent Graph Parsing arxiv preprint arxiv: (Isozaki et al., 2010) Hideki Isozaki, Tsutomu Hirao, Kevin Duh, Katsuhito Sudoh, and Hajime Tsukada Automatic Evaluation of Translation Quality for Distant Language Pairs. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages (Ji et al., 2016) Shihao Ji, S. V. N. Vishwanathan, Nadathur Satish, Michael J. Anderson, and Pradeep Dubey BlackOut: Speeding up Recurrent Neural Network Language Models With Very Large Vocabularies. In Proceedings of the 4th International Conference on Learning Representations. (Johnson et al., 2016) Melvin Johnson, Mike Schuster, Quoc V. Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, Macduff Hughes, Jeffrey Dean Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation. arxiv preprint arxiv: (Kim et al., 2017) Yoon Kim, Carl Denton, Luong Hoang, Alexander M. Rush Neural Machine Translation with Source-Side Latent Graph Parsing. arxiv preprint arxiv: (Liu et al., 2006) Yang Liu, Qun Liu, and Shouxun Lin Tree-to-string alignment template for statistical machine translation. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pages

37 (Luong et al., 2015a) Thang Luong, Ilya Sutskever, Quoc Le, Oriol Vinyals, and Wojciech Zaremba. 2015b. Addressing the Rare Word Problem in Neural Machine Translation. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pages (Luong et al., 2015b) Thang Luong, Hieu Pham, and Christopher D. Manning Effective Approaches to Attention-based Neural Machine Translation. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages (Luong et al., 2015c) Minh-Thang Luong, Quoc V. Le, Ilya Sutskever, Oriol Vinyals, Lukasz Kaiser Multi-task Sequence to Sequence Learning. In Proceedings of the 4th International Conference on Learning Representations. (Miyao and Tsujii, 2008) Yusuke Miyao and Jun ichi Tsujii Feature Forest Models for Probabilistic HPSG Parsing. Computational Linguistics, 34(1): (Neubig et al., 2014) Graham Neubig and Kevin Duh On the elements of an accurate tree-tostring machine translation system. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages (Neubig et al., 2015) Graham Neubig, Makoto Morishita, and Satoshi Nakamura Neural Reranking Improves Subjective Quality of Machine Translation: NAIST at WAT2015. In Proceedings of the 2nd Workshop on Asian Translation (WAT2015), pages (Sutskever et al., 2014) Ilya Sutskever, Oriol Vinyals, and Quoc V. Le Sequence to Sequence Learning with Neural Networks. In Advances in Neural Information Processing Systems 27, pages

38 (Sennrich et al., 2016a) Rico Sennrich, Barry Haddow, and Alexandra Birch Neural machine translation of rare words with subword units. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, pages (Sennrich et al., 2016b) Rico Sennrich, Barry Haddow, and Alexandra Birch Controlling Politeness in Neural Machine Translation via Side Constraints. In Proceedings of Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, pages (Sennrich et al., 2016c) Rico Sennrich and Barry Haddow Linguistic input features improve neural machine translation. In Proceedings of the First Conference on Machine Translation, pages (Papineni et al., 2002) Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu BLEU: A Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pages (Wu et al., 2016) Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, Jeff Klingner, Apurva Shah, Melvin Johnson, Xiaobing Liu, Lukasz Kaiser, Stephan Gouws, Yoshikiyo Kato, Taku Kudo, Hideto Kazawa, Keith Stevens, George Kurian, Nishant Patil, Wei Wang, Cliff Young, Jason Smith, Jason Riesa, Alex Rudnick, Oriol Vinyals, Greg Corrado, Macduff Hughes, and Jeffrey Dean Google s neural machine translation system: Bridging the gap between human and machine translation. arxiv preprint arxiv:

sequence to sequence, B3TB2006, i

B3TB2006 2017 3 31 sequence to sequence, B3TB2006, 2017 3 31. i A Study on a Style Control for Dialogue Response Generation Reina Akama Abstract We propose a new dialogue response generation model combining