{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:31:01Z","timestamp":1791333061942,"version":"4.3.1"},"reference-count":162,"publisher":"MIT Press","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computational Linguistics"],"published-print":{"date-parts":[[2016,3]]},"abstract":"<jats:p>In statistical machine translation (SMT), the optimization of the system parameters to maximize translation accuracy is now a fundamental part of virtually all modern systems. In this article, we survey 12 years of research on optimization for SMT, from the seminal work on discriminative models (Och and Ney 2002) and minimum error rate training (Och 2003), to the most recent advances. Starting with a brief introduction to the fundamentals of SMT systems, we follow by covering a wide variety of optimization algorithms for use in both batch and online optimization. Specifically, we discuss losses based on direct error minimization, maximum likelihood, maximum margin, risk minimization, ranking, and more, along with the appropriate methods for minimizing these losses. We also cover recent topics, including large-scale optimization, nonlinear models, domain-dependent optimization, and the effect of MT evaluation measures or search on optimization. Finally, we discuss the current state of affairs in MT optimization, and point out some unresolved problems that will likely be the target of further research in optimization for MT.<\/jats:p>","DOI":"10.1162\/coli_a_00241","type":"journal-article","created":{"date-parts":[[2016,2,23]],"date-time":"2016-02-23T19:58:22Z","timestamp":1456257502000},"page":"1-54","source":"Crossref","is-referenced-by-count":16,"title":["Optimization for Statistical Machine Translation: A Survey"],"prefix":"10.1162","volume":"42","author":[{"given":"Graham","family":"Neubig","sequence":"first","affiliation":[{"name":"Graduate School of Information Science Nara Institute of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taro","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Google Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","reference":[{"key":"R1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273501"},{"key":"R2","unstructured":"Banerjee, Satanjeev and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pages 65\u201372, Ann Arbor, MI."},{"key":"R3","unstructured":"Bazrafshan, Marzieh, Tagyoung Chung, and Daniel Gildea. 2012. Tuning as linear regression. In Proceedings of HLT\/NAACL, pages 543\u2013547, Montr\u00e9al."},{"key":"R4","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1979.1675432"},{"key":"R5","unstructured":"Berger, Adam L., Vincent J. Della Pietra, and Stephen A. Della Pietra. 1996. A maximum entropy approach to natural language processing. Computational Linguistics, 22:39\u201371."},{"key":"R6","unstructured":"Blunsom, Phil, Trevor Cohn, and Miles Osborne. 2008. A discriminative latent variable model for statistical machine translation. In Proceedings of ACL\/HLT, pages 200\u2013208, Columbus, OH."},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613746"},{"key":"R8","doi-asserted-by":"crossref","unstructured":"Bojar, Ondrej, Christian Buck, Christian Federmann, Barry Haddow, Philipp Koehn, Johannes Leveling, Christof Monz, Pavel Pecina, Matt Post, Herve Saint-Amand, Radu Soricut, Lucia Specia, and Ale\u0161 Tamchyna. 2014. Findings of the 2014 workshop on statistical machine translation. In Proceedings of WMT, pages 12\u201358, Baltimore, MD.","DOI":"10.3115\/v1\/W14-3302"},{"key":"R10","unstructured":"Brown, Peter F., Vincent J. Della Pietra, Stephen A. Della Pietra, and Robert L. Mercer. 1993. The mathematics of statistical machine translation: Parameter estimation. Computational Linguistics, 19(2):263\u2013311."},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102363"},{"key":"R12","unstructured":"Callison-Burch, Chris, Philipp Koehn, Christof Monz, and Omar Zaidan. 2011. Findings of the 2011 workshop on statistical machine translation. In Proceedings of WMT, pages 22\u201364, Edinburgh."},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"R14","doi-asserted-by":"crossref","unstructured":"Cer, Daniel, Dan Jurafsky, and Christopher D. Manning. 2008. Regularization and search for minimum error rate training. In Proceedings of WMT, pages 26\u201334, Columbus, OH.","DOI":"10.3115\/1626394.1626398"},{"key":"R15","unstructured":"Cer, Daniel, Christopher D. Manning, and Daniel Jurafsky. 2010. The best lexical metric for phrase-based statistical MT system optimization. In Proceedings of HLT\/NAACL, pages 555\u2013563, Los Angeles, CA."},{"key":"R16","unstructured":"Chappelier, Jean-C\u00e9dric and Martin Rajman. 1998. A generalized CYK algorithm for parsing stochastic CFG. In Proceedings of the 1st Workshop on Tabulation in Parsing and Deduction, pages 133\u2013137, Paris."},{"key":"R17","unstructured":"Chatterjee, Samidh and Nicola Cancedda. 2010. Minimum error rate training by sampling the translation lattice. In Proceedings of EMNLP, pages 606\u2013615, Cambridge, MA."},{"key":"R19","unstructured":"Cherry, Colin and George Foster. 2012. Batch tuning strategies for statistical machine translation. In Proceedings of HLT\/NAACL, pages 427\u2013436, Montr\u00e9al, Canada."},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2007.33.2.201"},{"key":"R21","unstructured":"Chiang, David. 2012. Hope and fear for discriminative training of statistical translation models. Journal of Machine Learning Research, 13:1159\u20131187."},{"key":"R22","doi-asserted-by":"crossref","unstructured":"Chiang, David, Kevin Knight, and Wei Wang. 2009. 11,001 new features for statistical machine translation. In Proceedings of HLT\/NAACL, pages 218\u2013226, Boulder, CO.","DOI":"10.3115\/1620754.1620786"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613747"},{"key":"R24","unstructured":"Chung, Tagyoung and Michel Galley. 2012. Direct error rate minimization for statistical machine translation. In Proceedings of WMT, pages 468\u2013479, Montr\u00e9al."},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00191"},{"key":"R26","unstructured":"Clark, Jonathan H., Chris Dyer, Alon Lavie, and Noah A. Smith. 2011. Better hypothesis testing for statistical machine translation: Controlling for optimizer instability. In Proceedings of ACL\/HLT, pages 176\u2013181, Portland, OR."},{"key":"R27","unstructured":"Clark, Jonathan H., Alon Lavie, and Chris Dyer. 2012. One system, many domains: Open-domain statistical machine translation via feature augmentation. In Proceedings of AMTA, San Diego, CA."},{"key":"R28","doi-asserted-by":"crossref","unstructured":"Collins, Michael. 2002. Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algorithms. In Proceedings of EMNLP, pages 1\u20138, Philadelphia, PA.","DOI":"10.3115\/1118693.1118694"},{"key":"R29","unstructured":"Collins, Michael, Amir Globerson, Terry Koo, Xavier Carreras, and Peter L. Bartlett. 2008. Exponentiated gradient algorithms for conditional random fields and max-margin Markov networks. Journal of Machine Learning Research, 9:1775\u20131822."},{"key":"R30","doi-asserted-by":"crossref","unstructured":"Collins, Michael and Brian Roark. 2004. Incremental parsing with the perceptron algorithm. In Proceedings of ACL, pages 111\u2013118, Barcelona.","DOI":"10.3115\/1218955.1218970"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.3115\/1610075.1610110"},{"key":"R32","unstructured":"Crammer, Koby, Ofer Dekel, Joseph Keshet, Shai Shalev-Shwartz, and Yoram Singer. 2006. Online passive-aggressive algorithms. Journal of Machine Learning Research, 7:551\u2013585."},{"key":"R33","unstructured":"Crammer, Koby, Alex Kulesza, and Mark Dredze. 2009. Adaptive regularization of weight vectors. In Proceedings of NIPS, pages 414\u2013422, Vancouver."},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.3.4-5.951"},{"key":"R35","doi-asserted-by":"crossref","unstructured":"Cui, Lei, Xilun Chen, Dongdong Zhang, Shujie Liu, Mu Li, and Ming Zhou. 2013. Multi-domain adaptation for SMT using multi-task learning. In Proceedings of EMNLP, pages 1055\u20131065, Seattle, WA.","DOI":"10.18653\/v1\/D13-1107"},{"key":"R36","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"R37","doi-asserted-by":"crossref","unstructured":"DeNero, John, David Chiang, and Kevin Knight. 2009. Fast consensus decoding over translation forests. In Proceedings of ACL\/IJCNLP, pages 567\u2013575, Singapore.","DOI":"10.3115\/1690219.1690226"},{"key":"R38","doi-asserted-by":"crossref","unstructured":"Denkowski, Michael, Chris Dyer, and Alon Lavie. 2014. Learning from post-editing: Online model adaptation for statistical machine translation. In Proceedings of EACL, pages 395\u2013404, Gothenburg.","DOI":"10.3115\/v1\/E14-1042"},{"key":"R39","doi-asserted-by":"crossref","unstructured":"Dreyer, Markus and Yuanzhe Dong. 2015. APRO: All-pairs ranking optimization for MT tuning. In Proceedings of NAACL, pages 1018\u20131023, Denver, CO.","DOI":"10.3115\/v1\/N15-1106"},{"key":"R40","unstructured":"Dreyer, Markus and Daniel Marcu. 2012. Hyter: Meaning-equivalent semantics for translation evaluation. In Proceedings of HLT\/NAACL, pages 162\u2013171, Montr\u00e9al."},{"key":"R41","doi-asserted-by":"publisher","DOI":"10.3115\/1699648.1699655"},{"key":"R42","unstructured":"Duchi, John, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12:2121\u20132159."},{"key":"R43","unstructured":"Duchi, John and Yoram Singer. 2009. Efficient online and batch learning using forward backward splitting. Journal of Machine Learning Research, 10:2899\u20132934."},{"key":"R44","doi-asserted-by":"crossref","unstructured":"Duh, Kevin and Katrin Kirchhoff. 2008. Beyond log-linear models: Boosted minimum error rate training for n-best re-ranking. In Proceedings of ACL\/HLT: Short Papers, pages 37\u201340, Columbus, OH.","DOI":"10.3115\/1557690.1557701"},{"key":"R45","unstructured":"Duh, Kevin, Katsuhito Sudoh, Xianchao Wu, Hajime Tsukada, and Masaaki Nagata. 2012. Learning to translate with multiple objectives. In Proceedings of ACL, pages 1\u201310, Jeju Island."},{"key":"R46","unstructured":"Dyer, Chris. 2010a. A Formal Model of Ambiguity and its Applications in Machine Translation. Ph.D. thesis, University of Maryland."},{"key":"R47","unstructured":"Dyer, Chris. 2010b. Two monolingual parses are better than one (synchronous parse). In Proceedings of HLT\/NAACL, pages 263\u2013266, Los Angeles, CA."},{"key":"R48","doi-asserted-by":"crossref","unstructured":"Dyer, Chris, Hendra Setiawan, Yuval Marton, and Philip Resnik. 2009. The University of Maryland statistical machine translation system for the Fourth Workshop on Machine Translation. In Proceedings of WMT, pages 145\u2013149, Athens.","DOI":"10.3115\/1626431.1626461"},{"key":"R49","unstructured":"Eidelman, Vladimir. 2012. Optimization strategies for online large-margin learning in machine translation. In Proceedings of the Seventh Workshop on Statistical Machine Translation, pages 477\u2013486, Montr\u00e9al."},{"key":"R50","unstructured":"Eidelman, Vladimir, Yuval Marton, and Philip Resnik. 2013. Online relative margin maximization for statistical machine translation. In Proceedings of ACL, pages 1116\u20131126, Sofia."},{"key":"R51","doi-asserted-by":"crossref","unstructured":"Eisner, Jason. 2002. Parameter estimation for probabilistic finite-state transducers. In Proceedings of ACL, pages 1\u20138, Philadelphia, PA.","DOI":"10.3115\/1073083.1073085"},{"key":"R52","unstructured":"Flanigan, Jeffrey, Chris Dyer, and Jaime Carbonell. 2013. Large-scale discriminative training for statistical machine translation using held-out line search. In Proceedings of HLT\/NAACL, pages 248\u2013258, Atlanta, GA."},{"key":"R53","doi-asserted-by":"crossref","unstructured":"Foster, George and Roland Kuhn. 2009. Stabilizing minimum error rate training. In Proceedings of WMT, pages 242\u2013249, Athens.","DOI":"10.3115\/1626431.1626478"},{"key":"R54","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.933"},{"key":"R55","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613824"},{"key":"R56","unstructured":"Galley, Michel and Chris Quirk. 2011. Optimal search for minimum error rate training. In Proceedings of EMNLP, pages 38\u201349, Edinburgh."},{"key":"R57","doi-asserted-by":"crossref","unstructured":"Galley, Michel, Chris Quirk, Colin Cherry, and Kristina Toutanova. 2013. Regularized minimum error rate training. In Proceedings of EMNLP, pages 1948\u20131959, Seattle, WA.","DOI":"10.18653\/v1\/D13-1201"},{"key":"R58","unstructured":"Gao, Jianfeng and Xiaodong He. 2013. Training MRF-based phrase translation models using gradient ascent. In Proceedings of HLT\/NAACL, pages 450\u2013459, Atlanta, GA."},{"key":"R59","unstructured":"Gesmundo, Andrea and James Henderson. 2011. Heuristic search for non-bottom-up tree structure prediction. In Proceedings of EMNLP, pages 899\u2013908, Edinburgh."},{"key":"R60","doi-asserted-by":"crossref","unstructured":"Gimpel, Kevin, Dhruv Batra, Chris Dyer, and Gregory Shakhnarovich. 2013. A systematic exploration of diversity in machine translation. In Proceedings of EMNLP, pages 1100\u20131111, Seattle, WA.","DOI":"10.18653\/v1\/D13-1111"},{"key":"R61","doi-asserted-by":"publisher","DOI":"10.3115\/1699510.1699539"},{"key":"R62","unstructured":"Gimpel, Kevin and Noah A. Smith. 2012. Structured ramp loss minimization for machine translation. In Proceedings of HLT\/NAACL, pages 221\u2013231, Montr\u00e9al."},{"key":"R63","doi-asserted-by":"crossref","unstructured":"Graham, Yvette, Timothy Baldwin, Alistair Moffat, and Justin Zobel. 2014. Is machine translation getting better over time? In Proceedings of EACL, pages 443\u2013451, Gothenburg.","DOI":"10.3115\/v1\/E14-1047"},{"key":"R64","doi-asserted-by":"crossref","unstructured":"Green, Spence, Daniel Cer, and Christopher Manning. 2014a. An empirical comparison of features and tuning for phrase-based machine translation. In Proceedings of WMT, pages 466\u2013476, Baltimore, MD.","DOI":"10.3115\/v1\/W14-3360"},{"key":"R65","unstructured":"Green, Spence, Sida Wang, Daniel Cer, and Christopher D. Manning. 2013. Fast and adaptive online training of feature-rich translation models. In Proceedings of ACL, pages 311\u2013321, Sofia."},{"key":"R66","doi-asserted-by":"crossref","unstructured":"Green, Spence, Sida I. Wang, Jason Chuang, Jeffrey Heer, Sebastian Schuster, and Christopher D. Manning. 2014b. Human effort and machine learnability in computer aided translation. In Proceedings of EMNLP, pages 1225\u20131236, Doha.","DOI":"10.3115\/v1\/D14-1130"},{"key":"R67","unstructured":"Haddow, Barry. 2013. Applying pairwise ranked optimization to improve the interpolation of translation models. In Proceedings of HLT\/NAACL, pages 342\u2013347, Atlanta, GA."},{"key":"R68","unstructured":"Haddow, Barry, Abhishek Arun, and Philipp Koehn. 2011. SampleRank training for phrase-based machine translation. In Proceedings of WMT, pages 261\u2013271, Edinburgh."},{"key":"R69","doi-asserted-by":"crossref","unstructured":"Hasan, Sa\u0161a, Richard Zens, and Hermann Ney. 2007. Are very large N-best lists useful for SMT? In Proceedings of HLT\/NAACL, pages 57\u201360, Rochester, NY.","DOI":"10.3115\/1614108.1614123"},{"key":"R70","unstructured":"Hayashi, Katsuhiko, Taro Watanabe, Hajime Tsukada, and Hideki Isozaki. 2009. Structural support vector machines for log-linear approach in statistical machine translation. In Proceedings of IWSLT, pages 144\u2013151, Tokyo."},{"key":"R71","unstructured":"He, Xiaodong and Li Deng. 2012. Maximum expected BLEU training of phrase and lexicon translation models. In Proceedings of ACL, pages 292\u2013301, Jeju Island."},{"key":"R72","unstructured":"He, Yifan and Andy Way. 2009. Improving the objective function in minimum error rate training. In Proceedings of MT Summit, pages 238\u2013245, Ottawa."},{"key":"R73","doi-asserted-by":"crossref","unstructured":"Herbrich, Ralf, Thore Graepel, and Klaus Obermayer. 1999. Support vector learning for ordinal regression. In Proceedings of ICANN, pages 97\u2013102, Edinburgh.","DOI":"10.1049\/cp:19991091"},{"key":"R74","unstructured":"Hopkins, Mark and Jonathan May. 2011. Tuning as ranking. In Proceedings of EMNLP, pages 1352\u20131362, Edinburgh."},{"key":"R75","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390208"},{"key":"R76","unstructured":"Huang, Liang and David Chiang. 2007. Forest rescoring: Faster decoding with integrated language models. In Proceedings of ACL, pages 144\u2013151, Prague."},{"key":"R77","unstructured":"Huang, Liang, Suphan Fayong, and Yang Guo. 2012. Structured perceptron with inexact search. In Proceedings of HLT\/NAACL, pages 142\u2013151, Montr\u00e9al."},{"key":"R78","doi-asserted-by":"crossref","unstructured":"Huang, Liang, Kevin Knight, and Aravind Joshi. 2006. Statistical syntax-directed translation with extended domain of locality. In Proceedings of AMTA, pages 66\u201373, Cambridge, MA.","DOI":"10.3115\/1631828.1631829"},{"key":"R82","doi-asserted-by":"crossref","unstructured":"Koehn, Philipp, Hieu Hoang, Alexandra Birch, Chris Callison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, Chris Dyer, Ondrej Bojar, Alexandra Constantin, and Evan Herbst. 2007. Moses: Open source toolkit for statistical machine translation. In Proceedings of ACL: Demo and Poster Sessions, pages 177\u2013180, Prague.","DOI":"10.3115\/1557769.1557821"},{"key":"R83","doi-asserted-by":"crossref","unstructured":"Koehn, Philipp, Franz Josef Och, and Daniel Marcu. 2003. Statistical phrase-based translation. In Proceedings of HLT\/NAACL, pages 48\u201354, Edmonton.","DOI":"10.21236\/ADA461156"},{"key":"R84","doi-asserted-by":"crossref","unstructured":"Koehn, Philipp and Josh Schroeder. 2007. Experiments in domain adaptation for statistical machine translation. In Proceedings of WMT, pages 224\u2013227, Prague.","DOI":"10.3115\/1626355.1626388"},{"key":"R85","doi-asserted-by":"crossref","unstructured":"Kumar, Shankar, Wolfgang Macherey, Chris Dyer, and Franz Och. 2009. Efficient minimum error rate training and minimum Bayes-risk decoding for translation hypergraphs and lattices. In Proceedings of ACL\/IJCNLP, pages 163\u2013171, Singapore.","DOI":"10.3115\/1687878.1687903"},{"key":"R86","unstructured":"Lagarda, Antonio and Francisco Casacuberta. 2008. Applying boosting to statistical machine translation. In Proceedings of EAMT, pages 88\u201396, Hamburg."},{"key":"R87","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613823"},{"key":"R88","unstructured":"Li, Mu, Yinggong Zhao, Dongdong Zhang, and Ming Zhou. 2010. Adaptive development data selection for log-linear model in statistical machine translation. In Proceedings of COLING, pages 662\u2013670, Beijing."},{"key":"R89","doi-asserted-by":"publisher","DOI":"10.3115\/1699510.1699517"},{"key":"R91","unstructured":"Li, Zhifei, Ziyuan Wang, Jason Eisner, Sanjeev Khudanpur, and Brian Roark. 2011. Minimum imputed-risk: Unsupervised discriminative training for machine translation. In Proceedings of EMNLP, pages 920\u2013929, Edinburgh."},{"key":"R92","unstructured":"Liang, Huashen, Min Zhang, and Tiejun Zhao. 2012. Forced decoding for minimum error rate training in statistical machine translation. Journal of Computational Information Systems, 8(2):861\u2013868."},{"key":"R93","doi-asserted-by":"crossref","unstructured":"Liang, Percy, Alexandre Bouchard-C\u00f4t\u00e9, Dan Klein, and Ben Taskar. 2006. An end-to-end discriminative approach to machine translation. In Proceedings of COLING\/ACL, pages 761\u2013768, Sydney.","DOI":"10.3115\/1220175.1220271"},{"key":"R94","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220427"},{"key":"R95","unstructured":"Liu, Chang, Daniel Dahlmeier, and Hwee Tou Ng. 2011. Better evaluation metrics lead to better machine translation. In Proceedings of EMNLP, pages 375\u2013384, Edinburgh."},{"key":"R96","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"R97","unstructured":"Liu, Lemao, Hailong Cao, Taro Watanabe, Tiejun Zhao, Mo Yu, and Conghui Zhu. 2012. Locally training the log-linear model for SMT. In Proceedings of EMNLP\/CoNLL, pages 402\u2013411, Jeju Island."},{"key":"R98","doi-asserted-by":"crossref","unstructured":"Liu, Lemao and Liang Huang. 2014. Search-aware tuning for machine translation. In Proceedings of EMNLP, pages 1942\u20131952, Doha.","DOI":"10.3115\/v1\/D14-1209"},{"key":"R99","unstructured":"Liu, Lemao, Taro Watanabe, Eiichiro Sumita, and Tiejun Zhao. 2013. Additive neural networks for statistical machine translation. In Proceedings of ACL, pages 791\u2013801, Sofia."},{"key":"R100","unstructured":"Liu, Lemao, Tiejun Zhao, Taro Watanabe, Hailong Cao, and Conghui Zhu. 2012. Expected error minimization with ultraconservative update for SMT. In Proceedings of COLING: Posters, pages 723\u2013732, Mumbai."},{"key":"R101","unstructured":"Liu, Lemao, Tiejun Zhao, Taro Watanabe, and Eiichiro Sumita. 2013. Tuning SMT with a large number of features via online feature grouping. In Proceedings of IJCNLP, pages 279\u2013285, Nagoya."},{"key":"R102","unstructured":"Lo, Chi-kiu, Karteek Addanki, Markus Saers, and Dekai Wu. 2013. Improving machine translation by training against an automatic semantic frame based evaluation metric. In Proceedings of ACL: Short Papers, pages 375\u2013381, Sofia."},{"key":"R103","doi-asserted-by":"publisher","DOI":"10.1145\/1380584.1380586"},{"key":"R104","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613807"},{"key":"R105","unstructured":"Marton, Yuval and Philip Resnik. 2008. Soft syntactic constraints for hierarchical phrased-based translation. In Proceedings of ACL\/HLT, pages 1003\u20131011, Columbus, OH."},{"key":"R106","unstructured":"Mathur, Prashant, Cettolo Mauro, and Marcello Federico. 2013. Online learning approaches in computer assisted translation. In Proceedings of WMT, pages 301\u2013308, Sofia."},{"key":"R107","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219852"},{"key":"R108","unstructured":"McDonald, Ryan, Keith Hall, and Gideon Mann. 2010. Distributed training strategies for the structured perceptron. In Proceedings of HLT\/NAACL, pages 456\u2013464, Los Angeles, CA."},{"key":"R109","doi-asserted-by":"publisher","DOI":"10.3115\/1599081.1599155"},{"key":"R110","unstructured":"Nakov, Preslav, Francisco Guzman, and Stephan Vogel. 2012. Optimizing for sentence-level BLEU+1 yields short translations. In Proceedings of COLING, pages 1979\u20131994, Mumbai."},{"key":"R111","unstructured":"Nakov, Preslav, Francisco Guzm\u00e1n, and Stephan Vogel. 2013. A tale about pro and monsters. In Proceedings of ACL: Short Papers, pages 12\u201317, Sofia."},{"key":"R112","doi-asserted-by":"crossref","unstructured":"Neidert, Julia, Sebastian Schuster, Spence Green, Kenneth Heafield, and Christopher Manning. 2014. Stanford University's submissions to the WMT 2014 translation task. In Proceedings of WMT, pages 150\u2013156, Baltimore, MD.","DOI":"10.3115\/v1\/W14-3316"},{"key":"R113","doi-asserted-by":"crossref","unstructured":"Nguyen, Patrick, Milind Mahajan, and Xiaodong He. 2007. Training non-parametric features for statistical machine translation. In Proceedings of WMT, pages 72\u201379, Prague.","DOI":"10.3115\/1626355.1626365"},{"key":"R115","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075117"},{"key":"R116","doi-asserted-by":"crossref","unstructured":"Och, Franz Josef and Hermann Ney. 2002. Discriminative training and maximum entropy models for statistical machine translation. In Proceedings of ACL, pages 295\u2013302, Philadelphia, PA.","DOI":"10.3115\/1073083.1073133"},{"key":"R117","doi-asserted-by":"publisher","DOI":"10.1162\/089120103321337421"},{"key":"R118","doi-asserted-by":"crossref","unstructured":"Papineni, K. A. 1999. Discriminative training via linear programming. In Proceedings of ICASSP, pages 561\u2013564, Phoenix, AZ.","DOI":"10.1109\/ICASSP.1999.759722"},{"key":"R119","doi-asserted-by":"crossref","unstructured":"Papineni, Kishore, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation. In Proceedings of ACL, pages 311\u2013318, Philadelphia, PA.","DOI":"10.3115\/1073083.1073135"},{"key":"R120","doi-asserted-by":"publisher","DOI":"10.3115\/1699648.1699688"},{"key":"R121","unstructured":"Pecina, Pavel, Antonio Toral, and Josef van Genabith. 2012. Simple and effective parameter tuning for domain adaptation of statistical machine translation. In Proceedings of COLING, pages 2209\u20132224, Mumbai."},{"key":"R122","unstructured":"Peitz, Stephan, Arne Mauser, Joern Wuebker, and Hermann Ney. 2012. Forced derivations for hierarchical machine translation. In Proceedings of COLING: Posters, pages 933\u2013942, Mumbai."},{"key":"R125","unstructured":"Razmara, Majid and Anoop Sarkar. 2013. Stacking for statistical machine translation. In Proceedings of ACL: Short Papers, pages 334\u2013339, Sofia."},{"key":"R126","unstructured":"Recht, Benjamin, Christopher Re, Stephen Wright, and Feng Niu. 2011. Hogwild: A lock-free approach to parallelizing stochastic gradient descent. In Proceedings of NIPS, pages 693\u2013701, Vancouver."},{"key":"R127","unstructured":"Rosti, Antti-Veikko, Bing Zhang, Spyros Matsoukas, and Richard Schwartz. 2010. BBN system description for WMT10 system combination task. In Proceedings of WMT, pages 321\u2013326, Uppsala."},{"key":"R128","unstructured":"Rosti, Antti-Veikko, Bing Zhang, Spyros Matsoukas, and Richard Schwartz. 2011. Expected BLEU training for graphs: BBN system description for WMT11 system combination task. In Proceedings of WMT, pages 159\u2013165, Edinburgh."},{"key":"R129","unstructured":"Roth, Benjamin, Andrew McCallum, Marc Dymetman, and Nicola Cancedda. 2010. Machine translation using overlapping alignments and SampleRank. In Proceedings of AMTA, Denver, CO."},{"key":"R130","unstructured":"Saluja, Avneesh, Ian Lane, and Ying Zhang. 2012. Machine translation with binary feedback: A large-margin approach. In Proceedings of AMTA, San Diego, CA."},{"key":"R131","doi-asserted-by":"crossref","unstructured":"Sanchis-Trilles, Germ\u00e1n and Francisco Casacuberta. 2010. Log-linear weight optimisation via Bayesian adaptation in statistical machine translation. In Proceedings of COLING: Posters, pages 1077\u20131085, Beijing.","DOI":"10.1007\/978-3-642-14980-1_61"},{"key":"R132","unstructured":"Sankaran, Baskaran, Anoop Sarkar, and Kevin Duh. 2013. Multi-metric optimization using ensemble tuning. In Proceedings of HLT\/NAACL, pages 947\u2013957, Atlanta, GA."},{"key":"R133","doi-asserted-by":"publisher","DOI":"10.2478\/v10108-011-0016-z"},{"key":"R134","unstructured":"Setiawan, Hendra and Bowen Zhou. 2013. Discriminative training of 150 million translation parameters and its application to pruning. In Proceedings of HLT\/NAACL, pages 335\u2013341, Atlanta, GA."},{"key":"R135","unstructured":"Shen, Libin, Anoop Sarkar, and Franz Josef Och. 2004. Discriminative reranking for machine translation. In Proceedings of HLT\/NAACL, pages 177\u2013184, Boston, MA."},{"key":"R136","unstructured":"Simianer, Patrick, Stefan Riezler, and Chris Dyer. 2012. Joint feature selection in distributed stochastic learning for large-scale discriminative training in SMT. In Proceedings of ACL, pages 11\u201321, Jeju Island."},{"key":"R137","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143950"},{"key":"R138","doi-asserted-by":"publisher","DOI":"10.3115\/1273073.1273174"},{"key":"R139","unstructured":"Snover, Matthew, Bonnie Dorr, Richard Schwartz, Linnea Micciulla, and John Makhoul. 2006. A study of translation edit rate with targeted human annotation. In Proceedings of AMTA, pages 223\u2013231, Cambridge, MA."},{"key":"R140","unstructured":"Sokolov, Artem, Guillaume Wisniewski, and Francois Yvon. 2012a. Computing lattice BLEU oracle scores for machine translation. In Proceedings of EACL, pages 120\u2013129, Avignon."},{"key":"R142","unstructured":"Sokolov, Artem and Fran\u00e7ois Yvon. 2011. Minimum error rate training semiring. In Proceedings of EAMT, pages 241\u2013248, Leuven."},{"key":"R143","unstructured":"Suzuki, Jun, Kevin Duh, and Masaaki Nagata. 2011. Distributed minimum error rate training of SMT using particle swarm optimization. In Proceedings of IJCNLP, pages 649\u2013657, Chiang Mai."},{"key":"R144","doi-asserted-by":"crossref","unstructured":"Tan, Ming, Tian Xia, Shaojun Wang, and Bowen Zhou. 2013. A corpus level MIRA tuning strategy for machine translation. In Proceedings of EMNLP, pages 851\u2013856, Seattle, WA.","DOI":"10.18653\/v1\/D13-1083"},{"key":"R145","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102464"},{"key":"R146","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"R147","doi-asserted-by":"crossref","unstructured":"Tillman, Christoph. 2004. A unigram orientation model for statistical machine translation. In Proceedings of HLT\/NAACL, pages 101\u2013104, Boston, MA.","DOI":"10.21236\/ADA460258"},{"key":"R148","doi-asserted-by":"crossref","unstructured":"Tillmann, Christoph and Tong Zhang. 2006. A discriminative global training algorithm for statistical MT. In Proceedings of COLING\/ACL, pages 721\u2013728, Sydney.","DOI":"10.3115\/1220175.1220266"},{"key":"R149","unstructured":"Toutanova, Kristina and Byung-Gyu Ahn. 2013. Learning non-linear features for machine translation using gradient boosting machines. In Proceedings of ACL: Short Papers, pages 406\u2013411, Sofia."},{"key":"R150","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613792"},{"key":"R151","doi-asserted-by":"crossref","unstructured":"Turian, Joseph, Benjamin Wellington, and I. Dan Melamed. 2006. Scalable discriminative learning for natural language parsing and translation. In Proceedings of NIPS, pages 1409\u20131416, Vancouver.","DOI":"10.7551\/mitpress\/7503.003.0181"},{"key":"R152","unstructured":"Ueffing, Nicola, Gholamreza Haffari, and Anoop Sarkar. 2007. Transductive learning for statistical machine translation. In Proceedings of ACL, pages 25\u201332, Prague."},{"key":"R153","doi-asserted-by":"publisher","DOI":"10.3115\/1118693.1118714"},{"key":"R154","doi-asserted-by":"crossref","unstructured":"Venugopal, Ashish and Stephan Vogel. 2005. Considerations in maximum mutual information and minimum classification error training for statistical machine translation. In Proceedings of EAMT, pages 271\u2013279, Budapest.","DOI":"10.3115\/1654449.1654493"},{"key":"R155","doi-asserted-by":"crossref","unstructured":"Wang, Zhuoran, John Shawe-Taylor, and Sandor Szedmak. 2007. Kernel regression based machine translation. In Proceedings of HLT\/NAACL: Short Papers, pages 185\u2013188, Rochester, NY.","DOI":"10.3115\/1614108.1614155"},{"key":"R156","unstructured":"Watanabe, Taro. 2012. Optimized online rank learning for machine translation. In Proceedings of HLT\/NAACL, pages 253\u2013262, Montr\u00e9al."},{"key":"R157","unstructured":"Watanabe, Taro, Jun Suzuki, Hajime Tsukada, and Hideki Isozaki. 2007. Online large-margin training for statistical machine translation. In Proceedings of EMNLP\/CoNLL, pages 764\u2013773, Prague."},{"key":"R158","unstructured":"Wu, Dekai. 1997. Stochastic inversion transduction grammars and bilingual parsing of parallel corpora. Computational Linguistics, 23(3):377\u2013403."},{"key":"R159","unstructured":"Wuebker, Joern, Arne Mauser, and Hermann Ney. 2010. Training phrase translation models with leaving-one-out. In Proceedings of ACL, pages 475\u2013484, Uppsala."},{"key":"R160","unstructured":"Wuebker, Joern, Stephan Peitz, Andreas Guta, and Hermann Ney. 2014. The RWTH Aachen machine translation systems for IWSLT 2014. In Proceedings of IWSLT, pages 150\u2013154, Lake Tahoe, NV."},{"key":"R161","unstructured":"Xiang, Bing and Abraham Ittycheriah. 2011. Discriminative feature-tied mixture modeling for statistical machine translation. In Proceedings of ACL\/HLT, pages 424\u2013428, Portland, OR."},{"key":"R162","unstructured":"Xiao, Lin. 2010. Dual averaging methods for regularized stochastic learning and online optimization. Journal of Machine Learning Research, 11:2543\u20132596."},{"key":"R163","unstructured":"Xiao, Xinyan, Yang Liu, Qun Liu, and Shouxun Lin. 2011. Fast generation of translation forest for large-scale SMT discriminative training. In Proceedings of EMNLP, pages 880\u2013888, Edinburgh."},{"key":"R164","doi-asserted-by":"crossref","unstructured":"Xiao, Xinyan and Deyi Xiong. 2013. Max-margin synchronous grammar induction for machine translation. In Proceedings of EMNLP, pages 255\u2013264, Seattle, WA.","DOI":"10.18653\/v1\/D13-1026"},{"key":"R165","doi-asserted-by":"publisher","DOI":"10.3115\/1073012.1073079"},{"key":"R166","doi-asserted-by":"crossref","unstructured":"Yu, Heng, Liang Huang, Haitao Mi, and Kai Zhao. 2013. Max-violation perceptron and forced decoding for scalable MT training. In Proceedings of EMNLP, pages 1112\u20131123, Seattle, WA.","DOI":"10.18653\/v1\/D13-1112"},{"key":"R167","doi-asserted-by":"publisher","DOI":"10.3115\/1699510.1699518"},{"key":"R168","unstructured":"Zens, Richard, Sasa Hasan, and Hermann Ney. 2007. A systematic comparison of training criteria for statistical machine translation. In Proceedings of EMNLP\/CoNLL, pages 524\u2013532, Prague."},{"key":"R169","doi-asserted-by":"crossref","unstructured":"Zhao, Bing and Shengyuan Chen. 2009. A simplex Armijo downhill algorithm for optimizing statistical machine translation decoding parameters. In Proceedings of HLT\/NAACL: Short Papers, pages 21\u201324, Boulder, CO.","DOI":"10.3115\/1620853.1620860"},{"key":"R170","unstructured":"Zhao, Yinggong, Shujie Liu, Yangsheng Ji, Jiajun Chen, and Guodong Zhou. 2011. Transductive minimum error rate training for statistical machine translation. In Proceedings of IJCNLP, pages 641\u2013648, Chiang Mai."},{"key":"R171","doi-asserted-by":"publisher","DOI":"10.3115\/1610075.1610087"},{"key":"R172","unstructured":"Zinkevich, Martin, John Langford, and Alex J. Smola. 2009. Slow learners are fast. In Proceedings of NIPS, pages 2331\u20132339, Vancouver."}],"container-title":["Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/COLI_a_00241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T13:50:44Z","timestamp":1748785844000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/coli\/article\/42\/1\/1-54\/1527"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":162,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,3]]}},"alternative-id":["10.1162\/COLI_a_00241"],"URL":"https:\/\/doi.org\/10.1162\/coli_a_00241","relation":{},"ISSN":["0891-2017","1530-9312"],"issn-type":[{"value":"0891-2017","type":"print"},{"value":"1530-9312","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,3]]}}}