[1]  Vitaly Kuznetsov and
Mehryar Mohri.
Time series prediction and online learning. In Proceedings of The 29th Annual Conference on Learning Theory (COLT 2016). New York, NY, June 2016.

[2]  Mehryar Mohri and Scott
Yang.
Adaptive algorithms and datadependent guarantees for bandit convex optimization. In Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence (UAI 2016). New York, NY, June 2016.

[3]  Corinna Cortes, Mehryar Mohri,
and Andrés Muñoz Medina.
Adaptation algorithm and theory based on generalized discrepancy. Journal of Machine Learning Research (JMLR), to appear, 2016.

[4]  Vitaly Kuznetsov and
Mehryar Mohri.
Generalization bounds for nonstationary mixing processes. Machine Learning Journal, to appear, 2016. Springer, Heidelberg, Germany.

[5]  Mehryar Mohri and Scott Yang.
Accelerating optimization via adaptive prediction. In Nineteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2016). Cádiz, Spain, May 2016.

[6]  Giulia DeSalvo and Mehryar
Mohri.
Random composite forests. In Thirtieth AAAI Conference on Artificial Intelligence (AAAI 2016). AAAI Press, 2016.

[7]  Mehryar Mohri and
Andrés Muñoz Medina.
Learning algorithms for secondprice auctions with reserve. Journal of Machine Learning Research (JMLR), to appear, 2016.

[8]  Vitaly Kuznetsov and
Mehryar Mohri.
Learning theory and algorithms for forecasting nonstationary time series. In Advances in Neural Information Processing Systems (NIPS 2015). Montréal, Canada, 2015. MIT Press.

[9]  Mehryar Mohri and
Andrés Muñoz Medina.
Revenue optimization against strategic buyers. In Advances in Neural Information Processing Systems (NIPS 2015). Montréal, Canada, 2015. MIT Press.

[10]  Corinna Cortes, Vitaly
Kuznetsov, Mehryar Mohri, and Manfred K. Warmuth.
Online learning algorithms for path experts with nonadditive losses. In Proceedings of The 28th Annual Conference on Learning Theory (COLT 2015). Paris, France, July 2015.

[11]  Corinna Cortes, Vitaly
Kuznetsov, Mehryar Mohri, and Umar Syed.
Structural Maxent models. In Proceedings of the 32nd International Conference on Machine Learning (ICML 2015). Lille, France, July 2015.

[12]  Borja Balle Pigem and
Mehryar Mohri.
On the Rademacher complexity of weighted automata. In Proceedings of The 26th International Conference on Algorithmic Learning Theory (ALT 2015). volume 9355, pages 179193, Banff, Canada, October 2015. Springer, Heidelberg, Germany.

[13]  Giulia DeSalvo, Mehryar
Mohri, and Umar Syed.
Learning with deep cascades. In Proceedings of The 26th International Conference on Algorithmic Learning Theory (ALT 2015). volume 9355, pages 254269, Banff, Canada, October 2015. Springer, Heidelberg, Germany.

[14]  Mehryar Mohri and
Andrés Muñoz Medina.
Nonparametric revenue optimization for generalized secondprice auctions. In Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence (UAI 2015). Amsterdam, The Netherlands, July 2015.

[15]  Borja Balle Pigem and Mehryar
Mohri.
Learning weighted automata. In Proceedings of The 6th International Conference on Algebraic Informatics (CAI 2015). volume to appear, Stuttgart, Germany, September 2015. Springer, Heidelberg, Germany.

[16]  Corinna Cortes, Mehryar Mohri,
and Andrés Muñoz Medina.
Adaptation algorithm and theory based on generalized discrepancy. In Proceedings of the 21st ACM Conference on Knowledge Discovery and Data Mining (KDD 2015). Sydney, Australia, August 2015.

[17]  Corinna Cortes, Prasoon Goyal,
Vitaly Kuznetsov, and Mehryar Mohri.
Kernel extraction via voted risk minimization. Journal of Machine Learning Research (JMLR), 44:7289, 2015.

[18]  Mehryar Mohri, Afshin
Rostamizadeh, and Dmitry Storcheus.
Generalization bounds for supervised dimensionality reduction. Journal of Machine Learning Research (JMLR), 44:226241, 2015.

[19]  Mehryar Mohri, Michael Riley,
and Ananda Theertha Suresh.
Automata and graph compression. In IEEE International Symposium on Information Theory (ISIT 2015). Hong Kong, China, 2015.

[20]  Mehryar Mohri and Michael
Riley.
On the disambiguation of weighted automata. In Proceedings of the 20th International Conference on Implementation and Application of Automata (CIAA 2015). Umeå, Sweden, August 2015.

[21]  Mehryar Mohri and
Andrés Muñoz Medina.
Optimal regret minimization in postedprice auctions with strategic buyers. In Advances in Neural Information Processing Systems (NIPS 2014). Montréal, Canada, 2014. MIT Press.

[22]  Vitaly Kuznetsov, Mehryar
Mohri, and Umar Syed.
Multiclass deep boosting. In Advances in Neural Information Processing Systems (NIPS 2014). Montréal, Canada, 2014. MIT Press.

[23]  Mehryar Mohri and Scott Yang.
Conditional swap regret and conditional correlated equilibrium. In Advances in Neural Information Processing Systems (NIPS 2014). Montréal, Canada, 2014. MIT Press.

[24]  Vitaly Kuznetsov and
Mehryar Mohri.
Generalization bounds for time series prediction with nonstationary processes. In Proceedings of The 25th International Conference on Algorithmic Learning Theory (ALT 2014). volume 8776, pages 260274, Bled, Slovenia, October 2014. Springer, Heidelberg, Germany.

[25]  Corinna Cortes, Mehryar
Mohri, and Umar Syed.
Deep boosting. In Proceedings of the 31st International Conference on Machine Learning (ICML 2014). Beijing, China, June 2014.

[26]  Mehryar Mohri and
Andrés Muñoz Medina.
Learning theory and algorithms for revenue optimization in secondprice auctions with reserve. In Proceedings of the 31st International Conference on Machine Learning (ICML 2014). Beijing, China, June 2014.

[27]  Corinna Cortes, Vitaly
Kuznetsov, and Mehryar Mohri.
Ensemble methods for structured prediction. In Proceedings of the 31st International Conference on Machine Learning (ICML 2014). Beijing, China, June 2014.

[28]  Corinna Cortes and
Mehryar Mohri.
Domain adaptation and sample bias correction theory and algorithm for regression. Theoretical Computer Science, 519, 2014.

[29]  Corinna Cortes, Vitaly
Kuznetsov, and Mehryar Mohri.
Learning ensembles of structured prediction rules. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics (ACL 2014). Baltimore, MD, June 2014.

[30]  Corinna Cortes, Spencer
Greenberg, and Mehryar Mohri.
Relative deviation learning bounds and generalization with unbounded loss functions. ArXiv 1310.5796. October 2013.

[31]  Corinna Cortes, Marius Kloft,
and Mehryar Mohri.
Learning kernels using local Rademacher complexity. In Advances in Neural Information Processing Systems (NIPS 2013). Lake Tahoe, Nevada, 2013. MIT Press.

[32]  Spencer Greenberg and
Mehryar Mohri.
Tight lower bound on the probability of a binomial exceeding its expectation. Statistics and Probability Letters. 2013.

[33]  Corinna Cortes, Mehryar Mohri,
and Afshin Rostamizadeh.
Multiclass classification with maximum margin multiple kernel. In Proceedings of the Thirtieth International Conference on Machine Learning (ICML 2013). Atlanta, GA, June 2013.

[34]  Mehryar Mohri.
On the disambiguation of finite automata and functional transducers. International Journal of Foundations of Computer Science, 24(6):847862, 2013.

[35]  Mehryar Mohri and
Afshin Rostamizadeh.
Perceptron mistake bounds. ArXiv 1305.0208. March 2013.

[36]  Borja Balle and Mehryar Mohri.
Spectral learning of general weighted automata via constrained matrix completion. In Advances in Neural Information Processing Systems (NIPS 2012). Lake Tahoe, Nevada, 2012. MIT Press.

[37]  Stephen Boyd, Corinna Cortes,
Mehryar Mohri, and Ana Radovanovic.
Accuracy at the top. In Advances in Neural Information Processing Systems (NIPS 2012). Lake Tahoe, Nevada, 2012. MIT Press.

[38]  Mehryar Mohri and
Andrés Muñoz Medina.
New analysis and algorithm for learning with drifting distributions. In Proceedings of The 23rd International Conference on Algorithmic Learning Theory (ALT 2012). volume 7568, pages 124138, Lyon, France, October 2012. Springer, Heidelberg, Germany.

[39]  Mehryar Mohri, Afshin
Rostamizadeh, and Ameet Talwalkar.
Foundations of Machine Learning. The MIT Press. 2012.

[40]  Mehryar Mohri.
A disambiguation algorithm for finite automata and functional transducers. In Proceedings of the 17th International Conference on Implementation and Application of Automata (CIAA 2012). Porto, Portugal, 2012.

[41]  Corinna Cortes, Mehryar
Mohri, and Afshin Rostamizadeh.
Algorithms for learning kernels based on centered alignment. Journal of Machine Learning Research (JMLR), 13:795828, 2012.

[42]  Sanjiv Kumar, Mehryar Mohri,
and Ameet Talwalkar.
Sampling methods for the Nyström method. Journal of Machine Learning Research (JMLR), 13:9811006, 2012.

[43]  Sanjiv Kumar, Mehryar
Mohri, and Ameet Talwalkar.
Ensemble Nyström. In Cha Zhang and Yunqian Ma, editors, Ensemble Machine Learning. pages 203223. Springer, 2012.

[44]  Corinna Cortes and Mehryar
Mohri.
Domain adaptation in regression. In Proceedings of The 22nd International Conference on Algorithmic Learning Theory (ALT 2011). volume 6925, pages 308323, Espoo, Finland, October 2011. Springer, Heidelberg, Germany.

[45]  Cyril Allauzen, Corinna
Cortes, and Mehryar Mohri.
A dual coordinate descent algorithm for SVMs combined with rational kernels. International Journal of Foundations of Computer Science, 22(8):17611779, 2011.

[46]  Corinna Cortes, Mehryar Mohri,
and Afshin Rostamizadeh.
Ensembles of kernel predictors. In Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011). Barcelona, Spain, July 2011.

[47]  Mehryar Mohri and Ameet
Talwalkar.
Can matrix coherence be efficiently and accurately estimated?. In Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2011). Ft. Lauderdale, FL, April 2011.

[48]  Cyril Allauzen, Mehryar
Mohri, and Ashish Rastogi.
General algorithms for testing the ambiguity of finite automata and the doubletape ambiguity of finitestate transducers. International Journal of Foundations of Computer Science, 22(4), 2011.

[49]  Corinna Cortes, Yishay
Mansour, and Mehryar Mohri.
Learning bounds for importance weighting. In Advances in Neural Information Processing Systems (NIPS 2010). Vancouver, Canada, 2010. MIT Press.

[50]  Corinna Cortes, Mehryar Mohri,
and Afshin Rostamizadeh.
Generalization bounds for learning kernels. In Proceedings of the Twentyseventh International Conference on Machine Learning (ICML 2010). Haifa, Israel, June 2010.

[51]  Corinna Cortes, Mehryar
Mohri, and Afshin Rostamizadeh.
Twostage learning kernel methods. In Proceedings of the Twentyseventh International Conference on Machine Learning (ICML 2010). Haifa, Israel, June 2010.

[52]  Mehryar Mohri and
Afshin Rostamizadeh.
Stability bounds for stationary phimixing and betamixing processes. Journal of Machine Learning Research (JMLR), 11:798814, 2010.

[53]  Nir Ailon and Mehryar Mohri.
Preferencebased learning to rank. Machine Learning Journal, 8(23):189211, 2010. Springer, Heidelberg, Germany.

[54]  Cyril Allauzen, Corinna
Cortes, and Mehryar Mohri.
Largescale training of SVMs with automata kernels. In Proceedings of the 15th International Conference on Implementation and Application of Automata (CIAA 2010). volume 6482, pages 1727, Winnipeg, Canada, 2010.

[55]  Corinna Cortes, Mehryar Mohri,
and Ameet Talwalkar.
On the impact of kernel approximation on learning accuracy. In Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010). Sardinia, Italy, May 2010.

[56]  Mehryar Mohri, Pedro Moreno,
and Eugene Weinstein.
Discriminative topic segmentation of text and speech. In Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010). Sardinia, Italy, May 2010.

[57]  Bing Bai, Jason Weston, David
Grangier, Ronan Collobert, Corinna Cortes, and Mehryar Mohri.
Half transductive ranking. In Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010). Sardinia, Italy, May 2010.

[58]  Cyril Allauzen,
Shankar Kumar, Wolfgang Macherey, Mehryar Mohri, and Michael Riley.
Expected sequence similarity maximization. In Proceedings of the 11th Annual Conference of the North American Chapter of the Association for Computational Linguistics (HLTNAACL 2010). Los Angeles, CA, May 2010.

[59]  Sanjiv Kumar, Mehryar Mohri, and
Ameet Talwalkar.
Ensemble Nyström method. In Advances in Neural Information Processing Systems (NIPS 2009). Vancouver, Canada, 2009. MIT Press.

[60]  Gideon Mann, Ryan McDonald,
Mehryar Mohri, Nathan Silberman, and Daniel D. Walker.
Efficient largescale distributed training of conditional maximum entropy models. In Advances in Neural Information Processing Systems (NIPS 2009). Vancouver, Canada, 2009. MIT Press.

[61]  Corinna Cortes, Mehryar Mohri,
and Afshin Rostamizadeh.
Learning nonlinear combinations of kernels. In Advances in Neural Information Processing Systems (NIPS 2009). Vancouver, Canada, 2009. MIT Press.

[62]  Bing Bai, Jason Weston, David
Grangier, Ronan Collobert, Kunihiko Sadamasa, Yanjun Qi, Corinna Cortes, and
Mehryar Mohri.
Polynomial semantic indexing. In Advances in Neural Information Processing Systems (NIPS 2009). Vancouver, Canada, 2009. MIT Press.

[63]  Corinna Cortes, Patrick
Haffner, and Mehryar Mohri.
Des algorithmes d'apprentissage pour mieux classifier. Pour la Science, numéro 386, Décembre 2009.

[64]  Yishay Mansour, Mehryar
Mohri, and Afshin Rostamizadeh.
Domain adaptation: Learning bounds and algorithms. In Proceedings of The 22nd Annual Conference on Learning Theory (COLT 2009). Montréal, Canada, June 2009. Omnipress.

[65]  Corinna Cortes, Mehryar
Mohri, and Afshin Rostamizadeh.
L_{2} regularization for learning kernels. In Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence (UAI 2009). Montréal, Canada, June 2009.

[66]  Yishay Mansour, Mehryar
Mohri, and Afshin Rostamizadeh.
Multiple source adaptation and the Rényi divergence. In Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence (UAI 2009). Montréal, Canada, June 2009.

[67]  Sanjiv Kumar, Mehryar Mohri,
and Ameet Talwalkar.
On samplingbased approximate spectral decomposition. In Proceedings of the Twentysixth International Conference on Machine Learning (ICML 2009). Montréal, Canada, June 2009.

[68]  Mehryar Mohri, Pedro Moreno, and
Eugene Weinstein.
General suffix automaton construction algorithm and space bounds. Theoretical Computer Science, 410(37):35533562, 2009.

[69]  Cyril Allauzen and
Mehryar Mohri.
Nway composition of weighted finitestate transducers. International Journal of Foundations of Computer Science, 20(4):613627, 2009.

[70]  Mehryar Mohri, Pedro Moreno,
and Eugene Weinstein.
Efficient and robust music identification with weighted finitestate transducers. IEEE Transactions on Audio, Speech, and Language Processing, 18(1):197207, 2009.

[71]  Mehryar Mohri, Pedro
Moreno, and Eugene Weinstein.
A new quality measure for topic segmentation of text and speech. In Proceedings of the 10th Annual Conference of the International Speech Communication Association (Interspeech 2009). Brighton, UK, September 2009.

[72]  Sanjiv Kumar, Mehryar Mohri, and
Ameet Talwalkar.
Sampling techniques for the Nyström method. In Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS 2009). pages 304311, Clearwater Beach, Florida, April 2009.

[73]  Koby Crammer, Mehryar Mohri,
and Fernando Pereira.
Gaussian margin machines. In Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS 2009). pages 105112, Clearwater Beach, Florida, April 2009.

[74]  Mehryar Mohri.
Weighted automata algorithms. In Manfred Droste, Werner Kuich, and Heiko Vogler, editors, Handbook of Weighted Automata. Monographs in Theoretical Computer Science, pages 213254. Springer, 2009.

[75]  Cyril Allauzen and Mehryar
Mohri.
Linearspace computation of the editdistance between a string and a finite automaton. In London Algorithmics 2008: Theory and Practice. volume 11 of Texts in Algorithmics, dedicated to Maxime Crochemore on his 60th birthday. College Publications, June 2009.

[76]  Mehryar Mohri and
Afshin Rostamizadeh.
Rademacher complexity bounds for noni.i.d. processes. In Advances in Neural Information Processing Systems (NIPS 2008). pages 10971104, Vancouver, Canada, 2009. MIT Press.

[77]  Yishay Mansour, Mehryar Mohri,
and Afshin Rostamizadeh.
Domain adaptation with multiple sources. In Advances in Neural Information Processing Systems (NIPS 2008). pages 10411048, Vancouver, Canada, 2009. MIT Press.

[78]  Corinna Cortes, Mehryar Mohri,
Dmitry Pechyony, and Ashish Rastogi.
Stability analysis and learning bounds for transductive regression algorithms. ArXiv 0904.0814. April 2009.

[79]  Corinna Cortes, Mehryar Mohri,
and Afshin Rostamizadeh.
Learning sequence kernels. In Proceedings of IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2008), (invited lecture). Cancún, Mexico, October 2008.

[80]  Corinna Cortes, Mehryar Mohri,
Michael Riley, and Afshin Rostamizadeh.
Sample selection bias correction theory. In Proceedings of The 19th International Conference on Algorithmic Learning Theory (ALT 2008). volume 5254 of Lecture Notes in Computer Science, pages 3853, Budapest, Hungary, October 2008. Springer, Heidelberg, Germany.

[81]  Corinna Cortes and
Mehryar Mohri.
Learning with weighted transducers. In Proceedings of the Seventh International Workshop FiniteState Methods and Natural Language Processing (FSMNLP 2008), (invited lecture). Ispra, Italy, September 2008.

[82]  Cyril Allauzen, Mehryar Mohri,
and Ashish Rastogi.
General algorithms for testing the ambiguity of finite automata. In Proceedings of Twelfth International Conference Developments in Language Theory (DLT 2008). volume 5257 of Lecture Notes in Computer Science, Kyoto, Japan, September 2008. Springer, Heidelberg, Germany.

[83]  Nir Ailon and
Mehryar Mohri.
An efficient reduction of ranking to classification. In Proceedings of The 21st Annual Conference on Learning Theory (COLT 2008). Helsinki, Finland, July 2008. Omnipress.

[84]  Corinna Cortes, Mehryar Mohri,
Dmitry Pechyony, and Ashish Rastogi.
Stability of transductive regression algorithms. In Proceedings of the Twentyfifth International Conference on Machine Learning (ICML 2008). Helsinki, Finland, July 2008.

[85]  Cyril Allauzen, Mehryar Mohri,
and Ameet Talwalkar.
Sequence kernels for predicting protein essentiality. In Proceedings of the Twentyfifth International Conference on Machine Learning (ICML 2008). Helsinki, Finland, July 2008.

[86]  Cyril Allauzen and Mehryar
Mohri.
3way composition of weighted finitestate transducers. In Proceedings of the 13th International Conference on Implementation and Application of Automata (CIAA 2008). volume 5148 of Lecture Notes in Computer Science, pages 262273, San Francisco, California, July 2008. SpringerVerlag, Heidelberg, Germany.

[87]  Leonid Kontorovich,
Corinna Cortes, and Mehryar Mohri.
Kernel methods for learning languages. Theoretical Computer Science, 405:223236, 2008.

[88]  Mehryar Mohri and
Afshin Rostamizadeh.
Stability bounds for noni.i.d. processes. In Advances in Neural Information Processing Systems (NIPS 2007). Vancouver, Canada, 2008. MIT Press.

[89]  Corinna Cortes, Patrick
Haffner, and Mehryar Mohri.
A machine learning framework for spokendialog classification. In Larry Rabiner and Fred Juang, editors, Handbook on Speech Processing and Speech Communication, Part E: Speech recognition. SpringerVerlag, Heidelberg, Germany, 2008.

[90]  Corinna Cortes, Mehryar Mohri,
Ashish Rastogi, and Michael Riley.
On the computation of the relative entropy of probabilistic automata. International Journal of Foundations of Computer Science, 19(1):219242, 2008.

[91]  Mehryar Mohri, Fernando C. N.
Pereira, and Michael Riley.
Speech recognition with weighted finitestate transducers. In Larry Rabiner and Fred Juang, editors, Handbook on Speech Processing and Speech Communication, Part E: Speech recognition. SpringerVerlag, Heidelberg, Germany, 2008.

[92]  Nir Ailon and Mehryar Mohri.
An efficient reduction of ranking to classification. Technical Report TR2007903, Courant Institute of Mathematical Sciences, New York University, September 2007.

[93]  Cyril Allauzen and Mehryar
Mohri.
Nway composition of weighted finitestate transducers. Technical Report TR2007902, Courant Institute of Mathematical Sciences, New York University, August 2007.

[94]  Corinna Cortes, Leonid
Kontorovich, and Mehryar Mohri.
Learning languages with rational kernels. In Proceedings of The 20th Annual Conference on Learning Theory (COLT 2007). volume 4539 of Lecture Notes in Computer Science, pages 349364, San Diego, California, June 2007. Springer, Heidelberg, Germany.

[95]  Corinna Cortes, Mehryar
Mohri, and Ashish Rastogi.
Magnitudepreserving ranking algorithms. In Proceedings of the Twentyfourth International Conference on Machine Learning (ICML 2007). Oregon State University, Corvallis, OR, June 2007.

[96]  Mehryar Mohri, Pedro Moreno, and
Eugene Weinstein.
Factor automata of automata and applications. In Proceedings of the 12th International Conference on Implementation and Application of Automata (CIAA 2007). volume 4783 of Lecture Notes in Computer Science, pages 168179, Prague, Czech Republic, July 2007. SpringerVerlag, Heidelberg, Germany.

[97]  Mehryar Mohri, Pedro Moreno,
and Eugene Weinstein.
Robust music identification, detection, and analysis. In Proceedings of the 8th International Conference on Music Information Retrieval (ISMIR 2007). Vienna, Austria, September 2007.

[98]  Corinna Cortes, Mehryar Mohri,
and Ashish Rastogi.
An Alternative Ranking Problem for Search Engines. In Proceedings of the 6th Workshop on Experimental Algorithms (WEA 2007). volume 4525 of Lecture Notes in Computer Science, pages 121, Rome, Italy, June 2007. SpringerVerlag, Heidelberg, Germany.

[99]  Cyril Allauzen, Michael Riley,
Johan Schalkwyk, Wojciech Skut, and Mehryar Mohri.
OpenFst: a general and efficient weighted finitestate transducer library. In Proceedings of the 12th International Conference on Implementation and Application of Automata (CIAA 2007). volume 4783 of Lecture Notes in Computer Science, pages 1123, Prague, Czech Republic, July 2007. SpringerVerlag, Heidelberg, Germany.

[100]  Corinna Cortes, Mehryar Mohri,
and Ashish Rastogi.
L_{p} Distance and Equivalence of Probabilistic Automata. International Journal of Foundations of Computer Science, 18(4):761780, 2007.

[101]  Corinna Cortes and Mehryar
Mohri.
On Transductive Regression. In Advances in Neural Information Processing Systems (NIPS 2006). pages 305312, Vancouver, Canada, 2007. MIT Press.

[102]  Corinna Cortes, Mehryar Mohri,
and Jason Weston.
A General Regression Framework for Learning StringtoString Mappings. In Predicting Structured Data. The MIT Press, September 2007.

[103]  Leonid Kontorovich, Corinna
Cortes, and Mehryar Mohri.
Learning Linearly Separable Languages. In Proceedings of The 17th International Conference on Algorithmic Learning Theory (ALT 2006). volume 4264 of Lecture Notes in Computer Science, pages 288303, Barcelona, Spain, October 2006. Springer, Heidelberg, Germany.

[104]  Cyril Allauzen and
Mehryar Mohri.
A Unified Construction of the Glushkov, Follow, and Antimirov Automata. In Proceedings of the 31st International Symposium on Mathematical Foundations of Computer Science (MFCS 2006). volume 4162 of Lecture Notes in Computer Science, pages 110121, Stará Lesná, Slovakia, August 2006. SpringerVerlag, Heidelberg, Germany.

[105]  Corinna Cortes, Mehryar
Mohri, and Ashish Rastogi.
On the Computation of Some Standard Distances between Probabilistic Automata. In Proceedings of the 11th International Conference on Implementation and Application of Automata (CIAA 2006). volume 4094 of Lecture Notes in Computer Science, pages 137149, Taipei, Taiwan, August 2006. SpringerVerlag, Heidelberg, Germany.

[106]  Mehryar Mohri and Brian
Roark.
Probabilistic ContextFree Grammar Induction Based on Structural Zeros. In Proceedings of the Seventh Meeting of the Human Language Technology conference North American Chapter of the Association for Computational Linguistics (HLTNAACL 2006). New York, NY, June 2006.

[107]  Corinna Cortes, Mehryar Mohri,
Ashish Rastogi, and Michael Riley.
Efficient Computation of the Relative Entropy of Probabilistic Automata. In Proceedings of the 7th Latin American Symposium (LATIN 2006). volume 3887 of Lecture Notes in Computer Science, pages 323336, Valdivia, Chile, March 2006. SpringerVerlag, Heidelberg, Germany.

[108]  Mehryar Mohri and Richard
Sproat.
On a Common Fallacy in Computational Linguistics. In Mickael Suominen, Antti Arppe, Anu Airola, Orvokki Heinämäki, Matti Miestamo, Urho Määttä, Jussi Niemi, Kari K. Pitkänen and Kaius Sinnemäki, editor, A Man of Measure: Festschrift in Honour of Fred Karlsson on this 60th Birthday. pages 432439. SKY Journal of Linguistics, Volume 19, 2006.

[109]  Corinna Cortes and Mehryar
Mohri.
Moment Kernels for Regular Distributions. Machine Learning, 60(13):117134, September 2005.

[110]  Mehryar Mohri.
Local Grammar Algorithms. In Antti Arppe, Lauri Carlson, Krister Lindèn, Jussi Piitulainen, Mickael Suominen, Martti Vainio, Hanna Westerlund, and Anssi YliJyrä, editor, Inquiries into Words, Constraints, and Contexts. Festschrift in Honour of Kimmo Koskenniemi on his 60th Birthday. pages 8493. CSLI Publications, Stanford University, 2005.

[111]  Mehryar Mohri and Brian
Roark.
Structural Zeros versus Sampling Zeros. Technical Report CSEE05003, OGI School of Science & Engineering, Oregon Health & Science University, September 2005.

[112]  Joannès Vermorel and
Mehryar Mohri.
MultiArmed Bandit Algorithms and Empirical Evaluation. In Proceedings of the 16th European Conference on Machine Learning (ECML 2005). volume 3720 of Lecture Notes in Computer Science, pages 437448, Porto, Portugal, October 2005. Springer, Heidelberg, Germany.

[113]  Corinna Cortes, Mehryar Mohri,
and Jason Weston.
A General Regression Technique for Learning Transductions. In Proceedings of the TwentySecond International Conference on Machine Learning (ICML 2005). pages 153160, Bonn, Germany, August 2005.

[114]  Corinna Cortes and Mehryar
Mohri.
FiniteState Transducers in Computational Biology. In Tutorial presented at the 13th Annual International Conference on Intelligent Systems for Molecular Biology (ISMB 2005). Detroit, MI, June 2005.

[115]  Cynthia Rudin, Corinna Cortes,
Mehryar Mohri, and Robert E. Schapire.
MarginBased Ranking Meets Boosting in the Middle. In Proceedings of The 18th Annual Conference on Computational Learning Theory (COLT 2005). volume 3359 of Lecture Notes in Computer Science, pages 6378, Bertinoro, Italy, June 2005. Springer, Heidelberg, Germany.

[116]  Mehryar Mohri.
Statistical Natural Language Processing. In M. Lothaire, editor, Applied Combinatorics on Words. Cambridge University Press, 2005.

[117]  Cyril Allauzen, Mehryar
Mohri, and Brian Roark.
The Design Principles and Algorithms of a Weighted Grammar Library. International Journal of Foundations of Computer Science, 16(3):403421, 2005.

[118]  Izhak Shafran and Mehryar
Mohri.
A Comparison of Classifiers for Detecting Emotion from Speech. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2005). Philadelphia, Pennsylvania, March 2005.

[119]  Corinna Cortes and Mehryar
Mohri.
Confidence Intervals for the Area under the ROC Curve. In Advances in Neural Information Processing Systems (NIPS 2004). volume 17, Vancouver, Canada, 2005. MIT Press.

[120]  Cyril Allauzen and Mehryar
Mohri.
An Optimal PreDeterminization Algorithm for Weighted Transducers. Theoretical Computer Science, 328(12):318, November 2004.

[121]  Corinna Cortes and Mehryar
Mohri.
Distribution Kernels Based on Moments of Counts. In Proceedings of the TwentyFirst International Conference on Machine Learning (ICML 2004). Banff, Alberta, Canada, July 2004.

[122]  Corinna Cortes, Patrick
Haffner, and Mehryar Mohri.
Rational kernels: Theory and algorithms. Journal of Machine Learning Research (JMLR), 5:10351062, 2004.

[123]  Cyril Allauzen, Mehryar
Mohri, and Brian Roark.
A general weighted grammar library. In Ninth International Conference on Automata (CIAA 2004), Kingston, Canada, July 2224, 2004. volume 3317 of Lecture Notes in Computer Science, pages 2334. SpringerVerlag, BerlinNY, 2005.

[124]  Cyril Allauzen, Mehryar
Mohri, and Michael Riley.
Statistical modeling for unit selection in speech synthesis. In 42nd Meeting of the Association for Computational Linguistics (ACL 2004), Proceedings of the Conference. Barcelona, Spain, July 2004.

[125]  Mehryar Mohri.
Weighted FiniteState Transducer Algorithms: An Overview. In Carlos MartínVide, Victor Mitrana, and Gheorghe Paun, editors, Formal Languages and Applications. volume 148, VIII, 620 p., pages 551564. Springer, Berlin, 2004.

[126]  Cyril Allauzen, Mehryar
Mohri, and Brian Roark.
A General Weighted Grammar Library. In Proceedings of the Ninth International Conference on Automata (CIAA 2004). Kingston, Ontario, Canada, July 2004.

[127]  Cyril Allauzen, Mehryar
Mohri, and Murat Saraclar.
General Indexation of Weighted Automata Application to Spoken Utterance Retrieval. In Proceedings of the annual meeting of the Human Language Technology conference and North American Chapter of the Association for Computational Linguistics (HLT/NAACL 2004), Workshop on Interdisciplinary Approaches to Speech Indexing and Retrieval. pages 3340, Boston, Massachusetts, May 2004.

[128]  Cyril Allauzen, Mehryar
Mohri, Brian Roark, and Michael Riley.
A Generalized Construction of Integrated Speech Recognition Transducers. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2004). Montréal, Canada, May 2004.

[129]  Corinna Cortes and Mehryar
Mohri.
AUC Optimization vs. Error Rate Minimization. In Advances in Neural Information Processing Systems (NIPS 2003). volume 16, Vancouver, Canada, 2004. MIT Press.

[130]  Mehryar Mohri.
Learning from Uncertain Data. In Proceedings of The 16th Annual Conference on Computational Learning Theory (COLT 2003). volume 2777 of Lecture Notes in Computer Science, pages 656670, Washington D.C., August 2003. Springer, Heidelberg, Germany.

[131]  Corinna Cortes, Patrick
Haffner, and Mehryar Mohri.
Positive Definite Rational Kernels. In Proceedings of The 16th Annual Conference on Computational Learning Theory (COLT 2003). volume 2777 of Lecture Notes in Computer Science, pages 4156, Washington D.C., August 2003. Springer, Heidelberg, Germany.

[132]  Mehryar Mohri.
Editdistance of weighted automata: General definitions and algorithms. International Journal of Foundations of Computer Science, 14(6):957982, 2003.

[133]  Cyril Allauzen and
Mehryar Mohri.
Efficient algorithms for testing the twins property. Journal of Automata, Languages and Combinatorics, 8(2):117144, 2003.

[134]  Cyril Allauzen, Mehryar
Mohri, and Brian Roark.
Generalized Algorithms for Constructing Statistical Language Models. In 41st Meeting of the Association for Computational Linguistics (ACL 2003), Proceedings of the Conference, Sapporo, Japan. July 2003.

[135]  Corinna Cortes, Patrick
Haffner, and Mehryar Mohri.
Weighted Automata Kernels General Framework and Algorithms. In Proceedings of the 9th European Conference on Speech Communication and Technology (Eurospeech '03), Special Session Advanced Machine Learning Algorithms for Speech and Language Processing. Geneva, Switzerland, September 2003.

[136]  Cyril Allauzen and
Mehryar Mohri.
An Efficient PreDeterminization Algorithm. In Eighth International Conference on Automata (CIAA 2003), Santa Barbara, CA. volume 2759 of Lecture Notes in Computer Science, pages 8395. Springer, BerlinNY, July 2003.

[137]  Izhak Shafran, Michael Riley,
and Mehryar Mohri.
Voice Signatures. In Proceedings of The 8th IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2003). St. Thomas, U.S. Virgin Islands, November 2003.

[138]  Corinna Cortes, Patrick
Haffner, and Mehryar Mohri.
Lattice Kernels for SpokenDialog Classification. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2003). Hong Kong, April 2003.

[139]  Cyril Allauzen and
Mehryar Mohri.
Finitely Subsequential Transducers. International Journal of Foundations of Computer Science, 14(6):983994, 2003.

[140]  Cyril Allauzen and Mehryar
Mohri.
Generalized Optimization Algorithm for Speech Recognition Transducers. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2003). Hong Kong, April 2003.

[141]  Corinna Cortes, Patrick
Haffner, and Mehryar Mohri.
Rational Kernels. In Advances in Neural Information Processing Systems (NIPS 2002). volume 15, Vancouver, Canada, March 2003. MIT Press.

[142]  Mehryar Mohri.
EditDistance of Weighted Automata. In JeanMarc Champarnaud and Denis Maurel, editor, Seventh International Conference on Automata (CIAA 2002), Tours, France. volume 2608 of Lecture Notes in Computer Science, pages 123. Springer, BerlinNY, April 2003.

[143]  Cyril Allauzen and
Mehryar Mohri.
pSubsequentiable Transducers. In JeanMarc Champarnaud and Denis Maurel, editor, Seventh International Conference on Automata (CIAA 2002), Tours, France. volume 2608 of Lecture Notes in Computer Science, pages 2434. Springer, BerlinNY, April 2003.

[144]  Mehryar Mohri.
Semiring Frameworks and Algorithms for ShortestDistance Problems. Journal of Automata, Languages and Combinatorics, 7(3):321350, 2002.

[145]  Mehryar Mohri and Michael
Riley.
An Efficient Algorithm for the NBestStrings Problem. In Proceedings of the International Conference on Spoken Language Processing 2002 (ICSLP '02). Denver, Colorado, September 2002.

[146]  Stephan Kanthak, Hermann Ney,
Michael Riley, and Mehryar Mohri.
A Comparison of Two LVR Search Optimization Techniques. In Proceedings of the International Conference on Spoken Language Processing 2002 (ICSLP '02). Denver, Colorado, September 2002.

[147]  Mehryar Mohri and Michael
Riley.
Weighted FiniteState Transducers in Speech Recognition (Tutorial). In Proceedings of the International Conference on Spoken Language Processing 2002 (ICSLP '02). Denver, Colorado, September 2002.

[148]  Mehryar Mohri.
EditDistance of Weighted Automata. In Proceedings of the Seventh International Conference on Automata (CIAA 2002). Tours, France, July 2002.

[149]  Cyril Allauzen and Mehryar
Mohri.
pSubsequentiable Transducers. In Proceedings of the Seventh International Conference on Automata (CIAA 2002). Tours, France, July 2002.

[150]  Mehryar Mohri.
Generic EpsilonRemoval and Input EpsilonNormalization Algorithms for Weighted Transducers. International Journal of Foundations of Computer Science, 13(1):129143, 2002.

[151]  Mehryar Mohri.
Weighted Automata Algorithms (Tutorial). In Proceedings of the workshop Weighted Automata: Theory and Applications (WATA). Dresden, Germany, March 2002.

[152]  Cyril Allauzen and
Mehryar Mohri.
On the Determinizability of Weighted Automata and Transducers. In Proceedings of the workshop Weighted Automata: Theory and Applications (WATA). Dresden, Germany, March 2002.

[153]  Mehryar Mohri, Fernando C. N.
Pereira, and Michael Riley.
Weighted FiniteState Transducers in Speech Recognition. Computer Speech and Language, 16(1):6988, 2002.

[154]  Mehryar Mohri and Michael
Riley.
A Weight Pushing Algorithm for Large Vocabulary Speech Recognition. In Proceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech '01). Aalborg, Denmark, September 2001.

[155]  Mehryar Mohri.
Language Processing with Weighted Transducers. In Proceedings of the 8th annual conference Traitement Automatique des Langues Naturelles (TALN 2001). Tours, France, July 2001.

[156]  Mehryar Mohri.
Weighted Grammar Tools: the GRM Library. In Robustness in Language and Speech Technology. pages 165186. Kluwer Academic Publishers, The Netherlands, 2001.

[157]  Mehryar Mohri.
Generic EpsilonRemoval Algorithm for Weighted Automata. In Sheng Yu and Andrei Paun, editor, 5th International Conference on Automata (CIAA 2000), London Ontario, Canada. volume 2088 of Lecture Notes in Computer Science, pages 230242. SpringerVerlag, BerlinNY, 2001.

[158]  Mehryar Mohri and
MarkJan Nederhof.
Regular Approximation of ContextFree Grammars through Transformation. In Robustness in Language and Speech Technology. pages 153163. Kluwer Academic Publishers, The Netherlands, 2001.

[159]  Mehryar Mohri.
Generic EpsilonRemoval Algorithm for Weighted Automata. In Proceedings of the Fifth International Conference on Automata (CIAA 2000). London, Ontario, Canada, July 2000.

[160]  Mehryar Mohri.
Minimization Algorithms for Sequential Transducers. Theoretical Computer Science, 234:177201, March 2000.

[161]  Corinna Cortes and
Mehryar Mohri.
ContextFree Recognition with Weighted Automata. Grammars, 3(23), 2000.

[162]  Mehryar Mohri, Fernando C. N.
Pereira, and Michael Riley.
The Design Principles of a Weighted FiniteState Transducer Library. Theoretical Computer Science, 231:1732, January 2000.

[163]  Mehryar Mohri, Fernando
C. N. Pereira, and Michael Riley.
Weighted FiniteState Transducers in Speech Recognition. In Proceedings of the ISCA Tutorial and Research Workshop, Automatic Speech Recognition: Challenges for the new Millenium (ASR2000). Paris, France, September 2000.

[164]  Corinna Cortes and Mehryar
Mohri.
ContextFree Recognition with Weighted Automata. In Proceedings of the Sixth Meeting on Mathematics of Language (MOL6). Orlando, Florida, 1999.

[165]  Mark Beutnagel, Mehryar
Mohri, and Michael Riley.
Rapid Unit Selection from a Large Speech Corpus for Concatenative Speech Synthesis. In Proceedings of the 6th European Conference on Speech Communication and Technology (Eurospeech '99). Budapest, Hungary, 1999.

[166]  Mehryar Mohri and Michael
Riley.
Integrated ContextDependent Networks in Very Large Vocabulary Speech Recognition. In Proceedings of the 6th European Conference on Speech Communication and Technology (Eurospeech '99). Budapest, Hungary, 1999.

[167]  Mehryar Mohri.
Comments on Jelinek, Language modeling for speech recognition, by Frederick Jelinek. In Extended Finite State Models of Language. Cambridge University Press, Cambridge, 1999.

[168]  Mehryar Mohri and Michael
Riley.
Network Optimizations for Large Vocabulary Speech Recognition. Speech Communication, 28(1):112, 1999.

[169]  Mehryar Mohri.
General Algebraic Frameworks and Algorithms for ShortestDistance Problems. Technical Memorandum 98121010TM, AT&T Labs Research, 62 pages, 1998.

[170]  Mehryar Mohri.
Speech Processing. Graduate course, Columbia University, Department of Computer Science, New York, NY, 515 pages. 1998.

[171]  Mehryar Mohri and Fernando
C. N. Pereira.
Dynamic Compilation of Weighted ContextFree Grammars. In 36th Meeting of the Association for Computational Linguistics (ACL '98), Proceedings of the Conference, Montréal, Québec, Canada. pages 891897, 1998.

[172]  Mehryar Mohri, Michael Riley,
Don Hindle, Andrej Ljolje, and Fernando C. N. Pereira.
Full Expansion of ContextDependent Networks in Large Vocabulary Speech Recognition. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP '98). Seattle, Washington, 1998.

[173]  Mehryar Mohri, Fernando C. N.
Pereira, and Michael Riley.
A Rational Design for a Weighted FiniteState Transducer Library. In Derick Wood and Sheng Yu, editors, Proceedings of the Second International Workshop on Implementing Automata (WIA '97). volume 1436 of Lecture Notes in Computer Science, pages 144158. SpringerVerlag, BerlinNY, September 1998.

[174]  B. Buntschuh, C. C. Kamm,
G. DiFabbrizio, A. Abella, M. Mohri, S. Narayan, I. Zeljkovic, R. Sharp,
J. Wright, S. Marcus, J. Shaffer, R. Duncan, and J. G. Wilpon.
VPQ: A Spoken Language Interface to Large Scale Directory Information. In Proceedings of the 1998th International Conference on Spoken Language Processing (ICSLP '98). Sydney, Australia, 1998.

[175]  Mehryar Mohri.
StringMatching with Automata. Nordic Journal of Computing, 4(2):217231, Summer 1997.

[176]  Mehryar Mohri.
On the use of sequential transducers in natural language processing. In FiniteState Language Processing. The MIT Press, Cambridge, Massachusetts, 1997.

[177]  Mehryar Mohri.
FiniteState Transducers in Language and Speech Processing. Computational Linguistics, 23:2, 1997.

[178]  Mehryar Mohri and Michael
Riley.
Weighted Determinization and Minimization for Large Vocabulary Speech Recognition. In Proceedings of the 5th European Conference on Speech Communication and Technology (Eurospeech '97). Rhodes, Greece, 1997.

[179]  Mehryar Mohri, Fernando C. N.
Pereira, and Michael Riley.
A Rational Design for a Weighted FiniteState Transducer Library. In Proceedings of the Workshop on Implementing Automata (WIA '97), London, Ontario, Canada. University of Western Ontario, London, Ontario, Canada, September 1820 1997.

[180]  Michael Riley, Fernando C. N.
Pereira, and Mehryar Mohri.
Transducer Composition for ContextDependent Network Expansion. In Proceedings of the 5th European Conference on Speech Communication and Technology (Eurospeech '97). Rhodes, Greece, 1997.

[181]  Mehryar Mohri, Fernando C. N.
Pereira, and Michael Riley.
A Rational Design for a Weighted FiniteState Transducer Library. In Proceedings of the 7th Annual AT&T Software Symposium, September 1718, 1997. AT&T Labs, 1997.

[182]  Mehryar Mohri and Richard
Sproat.
An Efficient Compiler for Weighted Rewrite Rules. In 34th Meeting of the Association for Computational Linguistics (ACL '96), Proceedings of the Conference, Santa Cruz, California. Santa Cruz, California, 1996.

[183]  Mehryar Mohri, Fernando C. N.
Pereira, and Michael Riley.
Rational Power Series in Text and Speech Processing. Graduate course, University of Pennsylvania, Department of Computer Science, Philadelphia, PA. 1996.

[184]  Mehryar Mohri, Fernando C. N.
Pereira, and Michael Riley.
Weighted Automata in Text and Speech Processing. In Proceedings of the 12th biennial European Conference on Artificial Intelligence (ECAI96), Workshop on Extended finite state models of language. Budapest, Hungary, 1996. John Wiley and Sons, Chichester.

[185]  Mehryar Mohri.
On some Applications of FiniteState Automata Theory to Natural Language Processing. Journal of Natural Language Engineering, 2:120, 1996.

[186]  Mehryar Mohri, Michael Riley, and
Richard Sproat.
FiniteState Transducers in Language and Speech Processing. In Tutorial at the 16th International Conference on Computational Linguistics (COLING96). Copenhagen, Denmark, 1996. COLING.

[187]  Mehryar Mohri.
Matching Patterns of an Automaton. In Zvi Galil and Esko Ukkonen, editors, Proceedings of the 6th Annual Symposium on Combinatorial Pattern Matching (CPM '95). volume 937 of Lecture Notes in Computer Science, pages 286297, Espoo, Finland, July 57 1995. SpringerVerlag, BerlinNY.

[188]  Denis Maurel and
Mehryar Mohri.
Computation of French Temporal Expressions to Query Databases. In The First Workshop on the Applications of Natural language Processing to Databases. Versailles, France, 1995. FWANLPD.

[189]  Mehryar Mohri.
Review of les nouvelles syntaxes, grammaires d'unification et analyse du français by Anne Abeillé, 1993, Armand Colin, Paris, France. Lingvisticae Investigationes, 18(2):415418, 1994.

[190]  Mehryar Mohri.
Minimization of Sequential Transducers. In Maxime Crochemore and Dan Gusfield, editors, Proceedings of the 5th Annual Symposium on Combinatorial Pattern Matching (CPM '94). volume 807 of Lecture Notes in Computer Science, pages 151163, Asilomar, California, June 58 1994. SpringerVerlag, BerlinNY.

[191]  Mehryar Mohri.
Combinaisons appropriées dans les constructions complétives. Langages, Larousse: Paris, 115, 1994.

[192]  Denis Maurel and Mehryar
Mohri.
French Temporal Expressions: Recognition, Parsing and Real Computation. In Proceedings of the 10th Annual Conference of the UW Centre for the New Oxford English Dictionary and Text Research, Waterloo, Ontario, Canada. University of Waterloo, 1994.

[193]  Mehryar Mohri.
Reprise par une relative. In Proceedings of the International Conference Dépendance et intégration syntaxique, Bordeaux, France. Niemeyer, 1994.

[194]  Mehryar Mohri.
On some Applications of FiniteState Automata Theory to Natural Language Processing: Representation of Morphological Dictionaries, Compaction, and Indexation. Technical Report IGM 9422, Institut Gaspard Monge, NoisyleGrand, 1994.

[195]  Mehryar Mohri.
Compact Representations by FiniteState Transducers. In 32nd Meeting of the Association for Computational Linguistics (ACL '94), Proceedings of the Conference, Las Cruces, New Mexico. pages 204209, 1994.

[196]  Mehryar Mohri.
Syntactic Analysis by Local Grammars Automata: an Efficient Algorithm. In Proceedings of the International Conference on Computational Lexicography (COMPLEX 94). Linguistic Institute, Hungarian Academy of Science: Budapest, Hungary, 1994.

[197]  Mehryar Mohri.
Analyse et représentation par automates de structures syntaxiques composées: Application aux complétives (Thesis Abstract). Lingvisticae Investigationes, 17(2):431432, 1993.

[198]  Mehryar Mohri.
Réduction de complétive à un nom et article défini générique. Lingvisticae Investigationes, 17(1):8397, 1993.

[199]  Mehryar Mohri.
La coréférence et l'aspect. Lingvisticae Investigationes, 14(2):403412, 1990.
