北京大学学报(自然科学版) 第 53 卷 第2期 2017 年3月

[2] Pervouchine V, Li H, Lin B. Transliteration alignment // Su K Y, Su J, Wiebe J. Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference

136‒144 on Natural Language Processing of the AFNLP. Singapore: ACL, 2009: [3] Finch A, Liu L, Wang X, et al. Neural network transduction models in transliteration generation // Duan X Y, Banchs R E, Zhang M, et al. Proceedings

61‒66 of the Fifth Named Entity Workshop. Beijing: ACL, 2015: [4] Koehn P, Och F J, Marcu D. Statistical phrase-based

127‒ translation // Daelemans W, Osborne M. Proceedings of the HLT/NAACL. Edmondon: ACL, 2003: 133 [5] Stolcke A. SRILM — an extensible language modeling toolkit // Hansen JH L, Pellom B L. Proceedings

901‒904 of International Conference on Spoken Language Processing. Denver: Interspeech, 2002: [6] Chen S F, Goodman J T. An empirical study of smoothing techniques for language modeling. Technical Report TR-10-98. Cambridge: Computer Science Group, Harvard University, 1998 [7] Och F J, Ney H. A systematic comparison of various

19‒51 statistical alignment models. Computational Linguistics, 2003, 29(1): [8] Koehn P, Hoang H, Birch A, et al. Moses: open source toolkit for statistical machine translation // Carroll J A, Van den Bosch A, Zaenen A. Proceedings of the Annual Meeting of the Association for Computational

177‒180 Linguistics, Demonstration Session. Prague: ACL, 2007: [9] Li H Z, Ma B, Lee C H. A vector space modeling approach to spoken language identification. IEEE Transaction on Acoustic, Speech, Signal Processing, 2007, 15(1): 271–284 [10] Liu L, Finch A, Utiyama M, et al. Agreement on targetbidirectional LSTMS for sequence to sequence learning // Schuurmans D, Wellman M P. Proceedings

2630‒2637 of the Thirtieth AAAI Conference on Artificial Intelligence. Phoenix: AAAI, 2016: [11] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate // CORR. Ithaca, New York, 2014: abs/1409.0473 [12] Chen B, Zhang M, Li H, et al. A comparative study of hypothesis alignment and its improvement for machine translation system combination // Su K Y, Su

941‒948 J, Wiebe J. Proceedings of ACL-IJCNLP. Singapore: ACL, 2009: [13] Snover M, Dorr B, Schwartz R, et al. A study of

223‒231 translation edit rate with targeted human annotation // Proceeding of AMTA. Boston: AMTA, 2006: [14] Melamed I D. Models of translational equivalence

221‒249 among words. Computational Linguistics, 2000, 26 (2): [15] He X, Yang M, Gao J, et al. Indirect Hmm-based hypothesis alignment for combining outputs from

98‒107 machine translation systems // Lapata M, Ng H T. Proceedings of EMNLP. Hawaii: ACL, 2008: [16] Zeiler M D. ADADELTA: an adaptive learning rate method // CORR. Ithaca, New York, 2012: abs/1212. 5701 [17] Cheng Y, Shen S, He Z J, et al. Agreement-based joint training for bidirectional attention-based neural

2761‒2767 machine translation // Kambhampati S. Proceedings of IJCAI. New York: AAAI, 2016: