Machine translation is an important field of research and development. Word reordering is one of the main problems in machine translation. It is an important factor of quality and efficiency of machine translations and becomes more difficult when it deals with structurally divergent language pairs. To overcome this problem, we introduce a neural reordering model, using phrasal dependency trees which depict dependency relations among contiguous non-syntactic phrases. The model makes the use of reordering rules, which are automatically learned by a probabilistic neural network classifier from a reordered phrasal dependency tree bank. The proposed model combines the power of the lexical reordering and syntactic pre-ordering models by performing long-distance reorderings. The proposed reordering model is integrated into a standard phrase-based statistical machine translation system to translate input sentences. Our method is evaluated on syntactically divergent language-pairs, English Persian and English German using WMT07 benchmark. The results illustrate the superiority of the proposed method in terms of BLEU, TER and LRscore on both translation tasks. On average the proposed method retrieves a significant impact on precision and recall values respect to the hierarchical, lexicalized and distortion reordering models.
KoehnP.OchF.J. and MarcuD., Statistical phrase-based translation, in: Presented at the Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, Vol. 1, 2003.
2.
LernerU. and PetrovS., Source-Side Classifier Preordering for Machine Translation, presented at the EMNLP, 2013.
3.
KoehnP.HoangH.BirchA.Callison-BurchC.FedericoM.BertoldiN. et al., Moses: Open source toolkit for statistical machine translation, in: Presented at the Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions, 2007.
4.
FarziS.FailiH.KhadiviS. and MalekiJ., A Novel Reordering Model for Statistical Machine Translation, Research in Computing Science65 (2013), 51–64.
5.
KhalilovM. and FonollosaA.R., Syntax-based reordering for statistical machine translation, Computer Speech & Language25 (2011), 761–788.
6.
KhalilovM.FonollosaJ.A.R. and DrasM., A new subtree-transfer approach to syntax-based reordering for statistical machine translation, in: Presented at the Proc. of the 13th Annual Conference of the European Association for Machine Translation (EAMTâ€𝑇𝑀9), 2009.
7.
KhalilovM. and Sima’anK., Context-Sensitive Syntactic Source-Reordering by Statistical Transduction, presented at the IJCNLP, 2011.
8.
Miceli BaroneA.V. and AttardiG., Pre-reordering for machine translation using transition-based walks on dependency parse trees, in: Presented at the Proceedings of the Eighth Workshop on Statistical Machine Translation, 2013.
9.
TrombleR. and EisnerJ., Learning linear ordering problems for better translation, in: Presented at the Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2, Vol. 2, 2009.
10.
ZhangY.ZensR. and NeyH., Chunk-level reordering of source language sentences with automatically learned rules for statistical machine translation, in: Presented at the Proceedings of the NAACL-HLT 2007/AMTA Workshop on Syntax and Structure in Statistical Translation, 2007.
11.
FarziS.FailiH. and KhadiviS., A Syntactically-Informed Reordering Model for Statistical Machine Translation, to be presented in journal of experimental and theoretical artificial intelligence, 2014.
12.
XiongD.LiuQ. and LinS., Maximum entropy based phrase reordering model for statistical machine translation, in: Presented at the Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics, 2006.
13.
SocherR.PerelyginA.WuJ.Y.ChuangJ.ManningC.D.NgA.Y. et al., Recursive deep models for semantic compositionality over a sentiment treebank, in: Presented at the Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2013.
14.
SocherR.BauerJ.ManningC.D. and NgA.Y., Parsing with compositional vector grammars, in: Presented at the In Proceedings of the ACL Conference, 2013.
15.
MikolovT.SutskeverI.ChenK.CorradoG.S. and DeanJ., Distributed representations of words and phrases and their compositionality, in: Presented at the Advances in Neural Information Processing Systems, 2013.
16.
LiP.LiuY. and SunM., Recursive Autoencoders for ITG-Based Translation, presented at the EMNLP, 2013.
17.
KalchbrennerN. and BlunsomP., Recurrent Continuous Translation Models, presented at the EMNLP, 2013.
18.
BengioY.SchwenkH.SencalJ.-S.MorinF. and GauvainJ.-L., Neural probabilistic language models, in: Innovations in Machine Learning, ed: Springer, 2006, pp. 137–186.
19.
SocherR.ManningC.D. and NgA.Y., Learning continuous phrase representations and syntactic parsing with recursive neural networks, in: Presented at the Proceedings of the NIPS-2010 Deep Learning and Unsupervised Feature Learning Workshop, 2010.
20.
KoehnP., Europarl: A parallel corpus for statistical machine translation, presented at the MT summit, 2005.
HabashN., Syntactic preprocessing for statistical machine translation, MT Summit XI (2007), 215–222.
23.
HanD.Martnez-GomezP.MiyaoY.SudohK. and NagataM., Unlabeled Dependency Parsing Based Pre-reordering for Chinese-to-Japanese SMT, Journal of Natural Language Processing21 (2014).
24.
VisweswariahK.NavratilJ.SorensenJ.ChenthamarakshanV. and KambhatlaN., Syntax based reordering with automatically derived rules for improved statistical machine translation, in: Presented at the Proceedings of the 23rd International Conference on Computational Linguistics, 2010.
25.
ZhuZ., Weblio Pre-reordering Statistical Machine Translation System, in: Presented at the Proceedings of the 1st Workshop on Asian Translation (WAT2014), 2015.
26.
CollinsM.KoehnP. and KuerovI., Clause restructuring for statistical machine translation, in: Presented at the Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, 2005.
27.
PopovicM. and NeyH., POS-based word reorderings for statistical machine translation, in: Presented at the International Conference on Language Resources and Evaluation, 2006.
28.
CregoJ.M. and HabashN., Using shallow syntax information to improve word alignment and reordering for SMT, in: Presented at the Proceedings of the Third Workshop on Statistical Machine Translation, 2008.
29.
NiehuesJ. and KolssM., A POS-based model for long-range reorderings in SMT, in: Presented at the Proceedings of the Fourth Workshop on Statistical Machine Translation, 2009.
30.
GenzelD., Automatically learning source-side reordering rules for large scale machine translation, in: Presented at the Proceedings of the 23rd International Conference on Computational Linguistics, 2010.
31.
HerrmannT.NiehuesJ. and WaibelA., Combining Word Reordering Methods on different Linguistic Abstraction Levels for Statistical Machine Translation, in: Presented at the Proceedings of the Seventh Workshop on Syntax, Semantics and Structure in Statistical Translation, Altanta, Georgia, USA, June. Association for Computational Linguistics, 2010.
32.
HanD.Martnez-GomezP.MiyaoY.SudohK. and NagataM., Using unlabeled dependency parsing for pre-reordering for Chinese-to-Japanese statistical machine translation, in: Presented at the Proc. of the ACL Second Workshop on Hybrid Approaches to Translation, 2013.
33.
GotoI.UtiyamaM. and SumitaE., Post-Ordering by Parsing with ITG for Japanese-English Statistical Machine Translation, in: ACM Transactions on Asian Language Information Processing (TALIP), Vol. 12, 2013, p. 17.
34.
SudohK.WuX.DuhK.TsukadaH. and NagataM., Post-ordering in statistical machine translation, presented at the Proc. MT Summit, 2011.
35.
SudohK.WuX.DuhK.TsukadaH. and NagataM., Syntax-Based Post-Ordering for Efficient Japanese-to-English Translation, in: ACM Transactions on Asian Language Information Processing (TALIP), Vol. 12, 2013, p. 12.
36.
QuirkC.MenezesA. and CherryC., Dependency treelet translation: Syntactically informed phrasal SMT, in: Presented at the Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, 2005.
37.
ShenL.XuJ. and WeischedelR.M., A New String-to-Dependency Machine Translation Algorithm with a Target Dependency Language Model, in: ACL, 2008, pp. 577–585.
38.
GaoY.KoehnP. and BirchA., Soft dependency constraints for reordering in hierarchical phrase-based translation, in: Presented at the Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2011.
39.
ChiangD., A hierarchical phrase-based model for statistical machine translation, in: Presented at the Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, 2005.
40.
FarziS. and FailiH., A swarm-inspired re-ranker system for statistical machine translation, Computer Speech & Language29 (2015), 45–62.
41.
TesnièreL., Eléments de syntaxe structurale, Editions Klincksieck, 1959.
42.
BordesA.WestonJ.CollobertR. and BengioY., Learning structured embeddings of knowledge bases, in: Presented at the Conference on Artificial Intelligence, 2011.
43.
CollobertR. and WestonJ., A unified architecture for natural language processing: Deep neural networks with multitask learning, in: Presented at the Proceedings of the 25th International Conference on Machine Learning, 2008.
44.
CollobertR.WestonJ.BottouL.KarlenM.KavukcuogluK. and KuksaP., Natural language processing (almost) from scratch, The Journal of Machine Learning Research12 (2011), 2493–2537.
45.
GlorotX.BordesA. and BengioY., Domain adaptation for large-scale sentiment classification: A deep learning approach, in: Presented at the Proceedings of the 28th International Conference on Machine Learning (ICML-11), 2012.
46.
HuangE.H.SocherR.ManningC.D. and NgA.Y., Improving word representations via global context and multiple word prototypes, in: Presented at the Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers, Vol. 1, 2012.
47.
SocherR.PenningtonJ.HuangE.H.NgA.Y. and ManningC.D., Semi-supervised recursive autoencoders for predicting sentiment distributions, in: Presented at the Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2011.
48.
SchwenkH., Continuous space language models, Computer Speech & Language21 (2007), 492–518.
49.
GollerC. and KuchlerA., Learning task-dependent distributed representations by backpropagation through structure, in: Neural Networks, 1996, IEEE International Conference on, 1996, pp. 347–352.
50.
OchF.J. and NeyH., The alignment template approach to statistical machine translation, Computational Linguistics30 (2004), 417–449.
51.
MansouriA. and FailiH., State-of-the-art english to persian statistical machine translation system, in: Presented at the Artificial Intelligence and Signal Processing (AISP), 2012 16th CSI International Symposium on, 2012.
52.
BisazzaA. and FedericoM., Efficient solutions for word reordering in German-English phrase-based statistical machine translation, in: Proceedings of the Eighth Workshop on Statistical Machine Translation, 2013, pp. 440–451.
53.
StolckeA., SRILM-an extensible language modeling toolkit, presented at the INTERSPEECH, 2002.
54.
OchF.J. and NeyH., Improved statistical alignment models, in: Presented at the Proceedings of the 38th Annual Meeting on Association for Computational Linguistics, 2000.
55.
SnoverM.DorrB.SchwartzR.MicciullaL. and MakhoulJ., A study of translation edit rate with targeted human annotation, in: Presented at the Proceedings of association for machine translation in the Americas, 2006.
56.
BirchA. and OsborneM., LRscore for evaluating lexical and reordering quality in MT, in: Presented at the Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, 2010.
57.
OchF.J., Minimum error rate training in statistical machine translation, in: Presented at the Proceedings of the 41st Annual Meeting on Association for Computational Linguistics, Vol. 1, 2003.
58.
De MarneffeM.-C.MacCartneyB. and ManningC.D., Generating typed dependency parses from phrase structure parses, presented at the Proceedings of LREC, 2006.
