. .. Étiquetage-et-annotation-de-la-base-de-données, 110 3.3.2.1 Création d'une base d'apprentissage, 111 3.3.2.2 Création des bases de validation et de test, p.112

. Fig, Exemple de détection d'information avec 10 requêtes quelconques Le premier mot (Vincent) et la dernière séquence (le numéro de téléphone) sont incorrectement rejetés (FR)

. De-la-première-passe-d-'apprentissage, L'apprentissage conjoint peut donc être realisé en effectuant alternativement l'étape de fine-tuning de la couche de décision du réseau de neurones profond et un alignement des modèles sur les données d'apprentissage avec la combinaison hybride neuro-markovienne

]. T. Adamek, N. E. Connor, and A. F. Smeaton, Word matching using single closed contours for indexing handwritten historical documents, International Journal of Document Analysis and Recognition (IJDAR), vol.29, issue.2, pp.153-165, 2007.
DOI : 10.1007/s10032-006-0024-y

I. Altun, T. Tsochantaridis, and . Hofmann, Hidden markov support vector machines, Machine Learning, p.3, 2003.

]. G. Andrew-2006 and . Andrew, A hybrid Markov/semi-Markov conditional random field for sequence segmentation, Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, EMNLP '06, pp.465-472, 2006.
DOI : 10.3115/1610075.1610140

]. M. Arivazhagan, H. Srinivasan, and S. Srihari, A statistical approach to line segmentation in handwritten documents, Document Recognition and Retrieval XIV, p.76, 2007.
DOI : 10.1117/12.704538

]. L. Arnold, H. Paugham-moisy, and M. Sebag, Optimisation de la Topologie pour les Réseaux de Neurones Profonds, pp.1-4, 2010.

]. X. Aubert, An overview of decoding techniques for large vocabulary continuous speech recognition, Computer Speech & Language, vol.16, issue.1, pp.89-114, 2002.
DOI : 10.1006/csla.2001.0185

]. R. Baeza-yates and B. Ribeiro-neto, Modern information retrieval, p.13, 1999.

]. S. Basu, C. Chaudhuri, M. Kundu, M. Nasipuri, and D. K. Basu, Text line extraction from multi-skewed handwritten documents, Pattern Recognition, vol.40, issue.6, pp.1825-1839, 2007.
DOI : 10.1016/j.patcog.2006.10.002

]. L. Baum and T. Petrie, Statistical Inference for Probabilistic Functions of Finite State Markov Chains, The Annals of Mathematical Statistics, vol.37, issue.6, pp.1554-1563, 1966.
DOI : 10.1214/aoms/1177699147

]. L. Baum, An inequalty and associated maximization technique in statistical estimation of probabilistic functions of a Markov process, Inequalities, vol.3, pp.1-8, 1972.

]. I. Bazzi, J. Glass, and A. C. Smith, Modeling Out-Of-Vocabulary Words For Robust Speech Recognition, pp.56-140, 2000.

]. R. Bellman and S. E. Dreyfus, Applied Dynamic Programming, p.58, 1962.
DOI : 10.1515/9781400874651

C. Lecun, C. Nohl, and . Burges, LeRec : a NN/HMM hybrid for on-line handwriting recognition, Neural Comput, vol.7, issue.152, pp.1289-1303, 1995.

]. Y. Bengio, Learning Deep Architectures for AI, Foundations and Trends?? in Machine Learning, vol.2, issue.1, p.150, 2007.
DOI : 10.1561/2200000006

]. Y. Bengio, P. Lamblin, D. Popovici, and H. Larochelle, Greedy layer-wise training of deep networks, NIPS, pp.153-160, 2007.

]. Y. Bengio-2007c, Y. Bengio, and . Lecun, Scaling learning algorithms towards AI. Large-Scale Kernel Machines, pp.1-41, 2007.

F. Bengio, A. Bastien, N. Bergeron, T. M. Boulanger-lewandowski, Y. Breuel et al., Deep Learners Benefit More from Out-of-Distribution Examples, Journal of Machine Learning Research -Proceedings Track, vol.15, issue.173, pp.164-172, 2011.

]. R. Bertolami, M. Zimmermann, and H. Bunke, Rejection strategies for offline handwritten text line recognition A transformation for extracting new descriptors of shape. Models for the perception of speech and visual form, Pattern Recognition Letters, vol.27, issue.81, pp.61-128, 1967.

]. L. Bottou and P. Gallinari, A framework for the cooperation of learning algorithms. Citeseer, p.151, 1991.

]. H. Bourlard and N. Morgan, Hybrid HMM/ANN systems for speech recognition : Overview and new research directions Adaptive Processing of Sequences and Data Structures, pp.389-417, 1998.

]. A. Brakensiek and G. , Handwritten Address Recognition Using Hidden Markov Models. Reading and Learning, pp.103-122, 2004.
DOI : 10.1007/978-3-540-24642-8_7

]. L. Breiman, Random Forests, Machine Learning, pp.5-32, 2001.

]. D. Brodic, D. R. Milivojevic, and Z. N. Milivojevic, An Approach to a Comprehensive Test Framework for Analysis and Evaluation of Text Line Segmentation Algorithms, Sensors, vol.19, issue.12, pp.8782-8812, 2011.
DOI : 10.1016/j.patcog.2006.10.002

]. F. Camastra, A SVM-based cursive character recognizer, Pattern Recognition, vol.40, issue.12, pp.3721-3727, 2007.
DOI : 10.1016/j.patcog.2007.03.014

]. R. Casey and E. Lecolinet, A survey of methods and strategies in character segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.18, issue.7, pp.690-706, 1996.
DOI : 10.1109/34.506792

]. C. Chatelain, L. Heutte, and T. Paquet, Segmentation-driven recognition applied to numerical field extraction from handwritten incoming mail documents. Document Analysis System, LNCS, vol.3872, issue.87, pp.564-575, 2006.
URL : https://hal.archives-ouvertes.fr/hal-00435969

]. Chen and J. Wang, Segmentation of Single-or Multiple- Touching Handwritten Numeral String Using Background and Foreground Analysis, IEEE Trans. on PAMI, vol.22, issue.43, pp.1304-1317, 2000.

]. N. Bibliographie and . Chinchor, Named Entity Task Definition, Proceedings of the 7th Message Understanding Conference (MUC-7), pp.1-21, 1998.

]. S. Cho, Neural-Network Classifiers for Recognizing Totally Unconstrained Handwritten Numerals, Neural Networks, vol.8, issue.1, pp.43-53, 1997.

]. Y. Choi, C. Cardie, E. Riloff, and S. Patwardhan, Identifying sources of opinions with conditional random fields and extraction patterns, Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing , HLT '05, pp.355-362, 2005.
DOI : 10.3115/1220575.1220620

]. C. Choisy-2007 and . Choisy, Dynamic Handwritten Keyword Spotting Based on the NSHP-HMM, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), pp.242-246, 2007.
DOI : 10.1109/ICDAR.2007.4378712

]. R. Collobert, S. Bengio, and J. Mariéthoz, Torch : a modular machine learning software library, IDIAP Research Report, pp.2-46, 2002.

]. R. Collobert-2008, J. Collobert, and . Weston, A unified architecture for natural language processing, Proceedings of the 25th international conference on Machine learning, ICML '08, pp.160-167, 2008.
DOI : 10.1145/1390156.1390177

]. G. Congedo, G. Dimauro, S. Impedovo, and G. Pirlo, Segmentation of numeric strings, Proceedings of 3rd International Conference on Document Analysis and Recognition, p.1038, 1995.
DOI : 10.1109/ICDAR.1995.602080

]. A. Dempster-1977, N. M. Dempster, D. B. Laird, and . Rubin, Maximum Likelihood from Incomplete Data via the EM Algorithm, Journal of the Royal Statistical Society, vol.39, pp.1-38, 1977.

]. T. Do and T. Artières, Champs de Markov conditionnels pour le traitement de séquences, p.50, 2006.

]. R. Duda and P. E. Hart, Use of the Hough transformation to detect lines and curves in pictures, Communications of the ACM, vol.15, issue.1, pp.11-15, 1972.
DOI : 10.1145/361237.361242

]. G. Dupont, Apprentissage implicite pour la recherche d'information, p.12, 2011.

R. Yacoubi, C. Y. Sabourin, M. Suen, and . Gilloux, An HMM-based approach for off-line unconstrained handwritten word modeling and recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.21, issue.8, pp.752-760, 1999.
DOI : 10.1109/34.784288

M. Gilloux and J. Bertille, A Statistical Approach for Phrase Location and Recognition within a Text Line : An Application to Street Name Recognition, IEEE Trans. on PAMI, vol.24, issue.64, pp.172-188, 2002.

]. A. Elnagar and R. Alhajj, Segmentation of connected handwritten numeral strings, Pattern Recognition, vol.36, issue.3, pp.625-634, 2003.
DOI : 10.1016/S0031-3203(02)00097-3

]. D. Erhan, P. Manzagol, Y. Bengio, S. Bengio, and P. Vincent, The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training, Journal of Machine Learning Research -Proceedings Track, vol.5, pp.153-160, 2009.

]. D. Erhan, Y. Bengio, A. C. Courville, P. Manzagol, P. Vincent et al., Why Does Unsupervised Pre-training Help Deep Learning, Journal of Machine Learning Research, vol.11, pp.625-660, 2010.

S. Espana-boquera, M. J. Castro-bleda, J. Gorbe-moya, and F. Zamora-martinez, Improving Offline Handwritten Text Recognition with Hybrid HMM/ANN Models, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.33, issue.4, pp.767-779, 2011.
DOI : 10.1109/TPAMI.2010.141

]. J. Favata, S. Srihari, and V. Govindaraju, Off-line handwritten sentence recognition, Proc. IWFHR, pp.171-176, 1998.

]. S. Feng, R. Manmatha, and A. Mccallum, Exploring the Use of Conditional Random Field Models and HMMs for Historical Handwritten Document Recognition, Proceedings of the Second International Bibliographie Conference on Document Image Analysis for Libraries, pp.30-37, 2006.

]. S. Ferilli, Automatic digital document processing and management : Problems, algorithms and techniques, p.17, 2011.
DOI : 10.1007/978-0-85729-198-1

]. S. Fernández, A. Graves, and J. Schmidhuber, An Application of Recurrent Neural Networks to Discriminative Keyword Spotting, Artificial Neural Networks?ICANN 2007, pp.220-229, 2007.
DOI : 10.1007/978-3-540-74695-9_23

]. A. Finn and N. Kushmerick, Multi-level Boundary Classification for Information Extraction, European Conference on Machine Learning, pp.111-122, 2004.
DOI : 10.1007/978-3-540-30115-8_13

]. A. Fischer, A. Keller, V. Frinken, and H. Bunke, HMM-based Word Spotting in Handwritten Documents Using Subword Models, 2010 20th International Conference on Pattern Recognition, pp.3416-3419, 2010.
DOI : 10.1109/ICPR.2010.834

]. J. Flusser, On the independence of rotation moment invariants, Pattern Recognition, vol.33, issue.9, pp.1405-1410, 2000.
DOI : 10.1016/S0031-3203(99)00127-2

]. G. Fornay, The viterbi algorithm, Proceedings of the IEEE, vol.61, issue.3, pp.268-278, 1973.
DOI : 10.1109/PROC.1973.9030

]. V. Frinken, A. Fischer, and H. Bunke, A Novel Word Spotting Algorithm Using Bidirectional Long Short-Term Memory Neural Networks, Artificial Neural Networks in Pattern Recognition, pp.185-196, 2010.
DOI : 10.1007/978-3-642-12159-3_17

]. V. Frinken, A. Fischer, R. Manmatha, and H. Bunke, A Novel Word Spotting Method Based on Recurrent Neural Networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.34, issue.2, pp.211-224, 2012.
DOI : 10.1109/TPAMI.2011.113

]. N. Gorski, Optimizing error-reject trade off in recognition systems, Proceedings of the Fourth International Conference on Document Analysis and Recognition, pp.1092-1096, 1997.
DOI : 10.1109/ICDAR.1997.620677

N. Gorski, V. Anisimov, E. Augustin, O. Baret, S. Maximov-]-v et al., Holistic handwritten word recognition using temporal features derived from off-line images, Industrial bank check processing : the A2iA CheckReader TM . IJDAR, pp.196-206, 1996.

]. A. Graves and J. Schmidhuber, Framewise phoneme classification with bidirectional LSTM and other neural network architectures, Neural Networks, vol.18, issue.5-6, pp.602-610, 2005.
DOI : 10.1016/j.neunet.2005.06.042

]. A. Graves, S. Fernández, F. Gomez, and J. Schmidhuber, Connectionist temporal classification, Proceedings of the 23rd international conference on Machine learning , ICML '06, pp.369-376, 2006.
DOI : 10.1145/1143844.1143891

]. A. Graves, M. Liwicki, S. Fernández, R. Bertolami, H. Bunke et al., A Novel Connectionist System for Unconstrained Handwriting Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.31, issue.5, pp.855-868, 2009.
DOI : 10.1109/TPAMI.2008.137

]. R. Grishman and B. Sundheim, Design of the MUC-6 evaluation, Proceedings of the 6th Message Understanding Conference, pp.1-11, 1995.

]. R. Grishman, Information extraction : Techniques and challenges . Information Extraction A Multidisciplinary Approach to an Emerging Information Technology, pp.10-27, 1997.
DOI : 10.1007/3-540-63438-x_2

]. Z. Gu and N. Cercone, Segment-based hidden Markov models for information extraction, Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL , ACL '06, pp.481-488, 2006.
DOI : 10.3115/1220175.1220236

]. D. Guillevic and C. Y. Suen, Cursive Script Recognition : A Sentence Level Recognition Scheme, International Workshop on Frontiers of Handwriting Recognition, pp.216-223, 1994.

]. T. Ha, G. Kaufmann, and H. Bunke, Text Localisation and Handwriting Recognition, pp.1-23, 1996.

]. T. Ha and H. Bunke, Off-Line Handwritten Numeral String Recognition . Rapport technique, pp.1-13, 1997.
DOI : 10.1109/34.589216

]. L. Heutte-1997, P. Heutte, O. Barbosa-pereira, J. Bougeois, B. Moreau et al., Multi-Bank Check Recognition System : Consideration on The Numeral Amount Recognition Module, IJPRAI, vol.11, issue.23, pp.595-618, 1997.

]. L. Heutte, T. Paquet, J. V. Moreau, Y. Lecourtier, and C. Olivier, A structural/statistical feature based vector for handwritten character recognition, Pattern Recognition Letters, vol.19, issue.7, pp.629-641, 1998.
DOI : 10.1016/S0167-8655(98)00039-7

]. G. Hinton and T. J. Sejnowski, Learning and relearning in Boltzmann machines. Parallel distributed processing : explorations in the microstructure of cognition, pp.282-317, 1986.

]. G. Hinton, S. Osindero, and Y. Teh, A Fast Learning Algorithm for Deep Belief Nets, Neural Computation, vol.18, issue.7, pp.1527-1554, 2006.
DOI : 10.1162/jmlr.2003.4.7-8.1235

]. G. Hinton and R. R. Salakhutdinov, Reducing the Dimensionality of Data with Neural Networks, Science, vol.313, issue.5786, pp.504-507, 2006.
DOI : 10.1126/science.1127647

]. J. Hobbs and E. Riloff, Handbook of Natural Language Processing, chapter 21 : Information Extraction, pp.16-17, 2010.

]. J. Hopfield, Neural networks and physical systems with emergent collective computational abilities, Proceedings of the National Academy of Sciences, pp.2554-2558, 1982.

]. Hu, Visual pattern recognition by moment invariants, IEEE Trans. on Information Theory, vol.8, issue.2, pp.179-187, 1962.

]. S. Huffman, Learning information extraction patterns from examples, Learning for Natural Language Processing, pp.246-260, 1996.
DOI : 10.1007/3-540-60925-3_51

]. S. Jaeger, S. Manke, and A. Waibel, Npen++ : An On-Line Handwriting Recognition System, 7th International Workshop on Frontiers in Handwriting Recognition, pp.249-260, 2000.

]. A. Jain, Statistical pattern recognition: a review, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.22, issue.1, pp.4-37, 2000.
DOI : 10.1109/34.824819
URL : http://www.cs.colorado.edu/~mozer/courses/6622/papers/Statistical Patten Recognition Review.pdf

]. F. Johansen, Text categorization with support vector machines : Learning with many relevant features A Comparison of hybrid HMM architectures using global discriminative training, Machine Learning : ECML-98 Speech and Audio Processing, pp.137-142, 1996.

]. B. Juang and S. Katagiri, Discriminative learning for minimum error classification (pattern recognition), IEEE Transactions on Signal Processing, vol.40, issue.12, pp.3043-3054, 1992.
DOI : 10.1109/78.175747

]. R. Kapoor, D. Bagai, and T. S. Kamal, A new algorithm for skew detection and correction, Pattern Recognition Letters, vol.25, issue.11, pp.1215-1229, 2004.
DOI : 10.1016/j.patrec.2004.03.020

]. E. Kavallieratos, N. Antoniades, N. Fakotakis, and G. Kokkinakis, Extraction and recognition of handwritten alphanumeric characters from application forms, Proceedings of 13th International Conference on Digital Signal Processing, pp.695-698, 1997.
DOI : 10.1109/ICDSP.1997.628447

]. P. Keaton, H. Greenspan, and R. Goodman, Keyword spotting for cursive document retrieval, Proceedings Workshop on Document Image Analysis (DIA'97), pp.74-82, 1997.
DOI : 10.1109/DIA.1997.627095

]. C. Kenyon and H. Paugam-moisy, Multilayer neural networks and polyhedral dichotomies, Annals of Mathematics and Artificial Intelligence, vol.24, issue.1/4, pp.115-128, 1998.
DOI : 10.1023/A:1018997115206

]. Y. Kessentini, T. Paquet, and A. Benhamadou, Off-line handwritten word recognition using multi-stream hidden Markov models, Pattern Recognition Letters, vol.31, issue.1, pp.60-70, 2010.
DOI : 10.1016/j.patrec.2009.08.009
URL : https://hal.archives-ouvertes.fr/hal-00668271

]. K. Khurshid, C. Faure, and N. Vincent, Recherche de mots dans des images de documents par appariement de caractères. Colloque International Francophone sur l'Ecrit et le Document, p.36, 2008.

]. J. Kim and . Moldovan, Acquisition of semantic patterns for information extraction from corpora, Proceedings of 9th IEEE Conference on Artificial Intelligence for Applications, pp.171-176, 1993.
DOI : 10.1109/CAIA.1993.366645

]. G. Kim and V. Govindaraju, Recognition of Handwritten Phrases as Applied to Street Name Images, Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition, pp.459-81, 1996.

]. G. Kim and V. Govindaraju, Bankcheck Recognition Using Cross Validation Between Legal and Courtesy Amounts, IJPRAI, vol.11, issue.4, pp.657-674, 1997.

]. F. Kimura, S. Tsuruoka, Y. Miyake, and M. Shridhar, A Lexicon Directed Algorithm for Recognition of Unconstrained Handwritten Bibliographie Words, IEICE trans. on Information and Systems, vol.77, issue.57, pp.785-793, 1994.

]. F. Kimura, N. Kayahara, Y. Miyake, and M. Shridhar, Machine and human recognition of segmented characters from handwritten words, Proceedings of the Fourth International Conference on Document Analysis and Recognition, pp.866-80, 1997.
DOI : 10.1109/ICDAR.1997.620635

. Simon, The A2iA Intercheque System : Courtesy Amount and Legal Amount Recognition for French Checks, IJPRAI, vol.11, issue.38, pp.505-548, 1997.

]. S. Knerr and E. Augustin, A neural network-hidden Markov model hybrid for cursive word recognition, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170), pp.1518-1520, 1998.
DOI : 10.1109/ICPR.1998.711996

]. G. Koch, L. Heutte, and T. Paquet, Combination of Contextual Information for Handwritten Word Recognition, Ninth International Workshop on Frontiers in Handwriting Recognition, p.43, 2004.
DOI : 10.1109/IWFHR.2004.27

]. G. Koch, Catégorisation automatique de documents manuscrits : application aux courriers entrants, pp.29-78, 2006.

]. A. Koerich, Large vocabulary off-line handwritten word recognition, p.44, 2002.

]. A. Koerich, Y. Leydier, R. Sabourin, and C. Y. Suen, A hybrid large vocabulary handwritten word recognition system using neural networks with hidden Markov models, Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition, pp.99-104, 2002.
DOI : 10.1109/IWFHR.2002.1030893

]. A. Koerich, R. Sabourin, and C. Y. Suen, Large vocabulary off-line handwriting recognition: A survey, Pattern Analysis & Applications, vol.6, issue.2, pp.97-121, 2003.
DOI : 10.1007/s10044-002-0169-3

]. A. Kolcz, J. Alspector, M. Augusteijn, R. Carlson, and G. V. Popescu, A Line-Oriented Approach to Word Spotting in Handwritten Documents, Pattern Analysis & Applications, vol.3, issue.2, pp.153-168, 2000.
DOI : 10.1007/s100440070020

]. R. Korfhage, Information storage and retrieval, p.12, 2008.

]. A. Krogh, I. S. Mian, and D. Haussler, DNA, Advances in Information Systems and Management Science, pp.4768-4778, 1994.
DOI : 10.1093/nar/22.22.4768

]. J. Lafferty, A. Mccallum, and F. C. Pereira, Conditional Random Fields : Probabilistic Models for Segmenting and Labeling Sequence Data, Proceedings of the Eighteenth International Conference on Machine Learning, pp.282-289, 2001.

]. K. Lang, A. H. Waibel, and G. E. Hinton, A time-delay neural network architecture for isolated word recognition, Neural Networks, vol.3, issue.1, pp.23-43, 1990.
DOI : 10.1016/0893-6080(90)90044-L

]. H. Larochelle, Y. Bengio, J. Louradour, and P. Lamblin, Exploring Strategies for Training Deep Neural Networks, J. Mach. Learn. Res, vol.10, issue.159, pp.1-40, 2009.

V. Lavrenko, T. M. Rath, and R. Manmatha, Holistic word recognition for handwritten historical documents, First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings., pp.278-286, 2004.
DOI : 10.1109/DIAL.2004.1263256

Y. Lecun, O. Matan, B. Boser, J. S. Denker, D. Henderson et al., Handwritten Zip Code Recognition with Multilayer Networks, Proc. of the International Conference on Pattern Recognition, pp.35-40, 1990.

Y. Lecun, L. D. Jackel, L. Bottou, A. Brunot, C. Cortes et al., Comparison of learning algorithms for handwritten digit recognition, International Conference on Artificial Neural Networks, pp.53-60, 1995.

]. Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, Gradient-based learning applied to document recognition, Proceedings of the IEEE, vol.86, issue.11, pp.2278-2324, 1998.
DOI : 10.1109/5.726791

]. Y. Leydier, A. Ouji, F. Lebourgeois, and H. Emptoz, Towards an omnilingual word retrieval system for ancient manuscripts, Pattern Recognition, vol.42, issue.9, pp.2089-2105, 2009.
DOI : 10.1016/j.patcog.2009.01.026
URL : https://hal.archives-ouvertes.fr/hal-01437678

]. J. Lii, Use of character recognition and syntax in locating address paragraphs in complex documents, p.22, 1995.

L. Likforman-sulem and C. Faure, Extracting text lines in handwritten documents by perceptual grouping Advances in handwriting and drawing : a multidisciplinary approach, pp.117-135, 1994.

L. Likforman-sulem and C. Faure, Une méthode de résolution des conflits d'alignements pour la segmentation des documents manuscrits, Traitement du Signal, vol.12, issue.77, pp.541-549, 1995.

A. Sulem, B. Zahour, and . Taconet, Text line segmentation of historical documents: a survey, International Journal of Document Analysis and Recognition (IJDAR), vol.26, issue.6, pp.123-138, 2007.
DOI : 10.1109/TPAMI.2002.1039211

H. Liu, H. Sako, and . Fujisawa, Effects of Classifier Structures and Training Regimes on Integrated Segmentation and Recognition of Handwritten Numeral Strings, IEEE Trans. on PAMI, vol.26, issue.11, pp.1395-1407, 2004.

]. G. Lorette, Handwritting Recognition or reading ? What is the situation at the dawn of the 3rd Millenium ? IJDAR, pp.2-12, 1999.

]. G. Louloudis, B. Gatos, and I. , Text line and word segmentation of handwritten documents, Pattern Recognition, vol.42, issue.12, pp.3169-3183, 2009.
DOI : 10.1016/j.patcog.2008.12.016

]. F. Lüthy, T. Varga, and H. Bunke, Using Hidden Markov Models as a Tool for Handwritten Text Line Segmentation, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), pp.8-11, 2007.
DOI : 10.1109/ICDAR.2007.4378666

]. V. Madasu, M. Hafizuddin, M. Yusof, M. Hanmandlu, and K. Kubik, Automatic Extraction of Signatures from Bank Cheques and Other Documents, pp.591-600, 2003.

]. R. Manmatha, C. Han, E. M. Riseman-]-a, R. S. Manos, V. W. Manos et al., A Study On Out-Of- Vocabulary Word Modeling For A Segment-Based Keyword Spotting System, Word Spotting : A New Approach to Indexing Handwriting. CVPR, pp.631-637, 1996.

]. U. Marti and H. Bunke, Handwritten sentence recognition, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000, pp.467-470, 2000.
DOI : 10.1109/ICPR.2000.903584
URL : http://www.iam.unibe.ch/~marti/icpr2000.ps.gz

]. U. Marti and H. Bunke, Text line segmentation and word recognition in a system for general writer independent handwriting recognition, Proceedings of Sixth International Conference on Document Analysis and Recognition, pp.159-163, 2001.
DOI : 10.1109/ICDAR.2001.953775

]. Marti and H. Bunke, Using a Statistical Language Model to Improve the Performance of an HMM-Based Cursive Handwriting Recognition System, IJPRAI, vol.15, issue.85, pp.65-90, 2001.

M. and H. Bunke, The IAM-database : an English sentence database for offline handwriting recognition, IJDAR, vol.5, issue.34, pp.39-46, 2002.

]. S. Marukatat, T. Artires, P. Gallinari, and B. Dorizzi, Sentence recognition through hybrid neuro-Markovian modeling, Proceedings of Sixth International Conference on Document Analysis and Recognition, pp.731-735, 2001.
DOI : 10.1109/ICDAR.2001.953886
URL : https://www.researchgate.net/profile/Thierry_Artieres/publication/220860738_Sentence_Recognition_through_Hybrid_Neuro-Markovian_Modeling/links/004635361ea5c3c7d9000000.pdf

]. S. Marukatat, T. Artieres, P. Gallinari, and B. Dorizzi, Rejection measures for handwriting sentence recognition, Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition, pp.24-29, 2002.
DOI : 10.1109/IWFHR.2002.1030879

]. O. Matan-1992, H. S. Matan, J. Baird, C. J. Bromley, J. S. Burges et al., Reading handwritten digits: a ZIP code recognition system, Computer, vol.25, issue.7, pp.59-63, 1992.
DOI : 10.1109/2.144441

]. A. Mccallum-2005 and . Mccallum, A conditional random field for discriminatively-trained finite-state string edit distance, p.50, 2005.
DOI : 10.21236/ADA440386

]. W. Mcculloch and W. Pitts, A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biology, vol.5, issue.4, pp.115-133, 1943.

]. M. Minsky and S. Papert, Perceptrons : An introduction to computational geometry, p.142, 1969.

]. D. Bibliographie and . Moore, TODE : A Decoder for Continuous Speech Recognition, p.92, 2002.

]. M. Morita, R. Sabourin, F. Bortolozzi, and Y. Suen, Segmentation and recognition of handwritten dates: an HMM-MLP hybrid approach, International Journal on Document Analysis and Recognition, vol.6, issue.4, 2003.
DOI : 10.1007/s10032-003-0114-z

]. C. Myers and L. Rabiner, A level building dynamic time warping algorithm for connected word recognition, IEEE Transactions on Acoustics, Speech, and Signal Processing, vol.29, issue.2, pp.284-297, 1981.
DOI : 10.1109/TASSP.1981.1163527

N. and ]. S. Nicolas, Graphes aléatoires conditionnels pour l'extraction d'information dans les données complexes, p.76, 2006.

N. Nikolaou, M. Makridis, B. Gatos, N. Stamatopoulos, and N. Papamarkos, Segmentation of historical machine-printed documents using Adaptive Run Length Smoothing and skeleton segmentation paths, Image and Vision Computing, vol.28, issue.4, pp.590-604, 2010.
DOI : 10.1016/j.imavis.2009.09.013

]. D. Niyogi, S. Srihari, and V. Govindaraju, Analysis of printed forms. Handbook on Optical Character Recognition and Document Image Analysis, pp.330-342, 1996.

]. L. Oliveira, R. Sabourin, F. Bortolozzi, and C. Y. Suen, Automatic recognition of handwritten numerical strings: a recognition and verification strategy, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.24, issue.11, pp.1438-1454, 2002.
DOI : 10.1109/TPAMI.2002.1046154

]. L. Oliveira and R. Sabourin, Support Vector Machines for Handwritten Numerical String Recognition, Ninth International Workshop on Frontiers in Handwriting Recognition, pp.39-44, 2004.
DOI : 10.1109/IWFHR.2004.99
URL : http://www.livia.etsmtl.ca/people/soares/download/iwfhr-svm.pdf

]. U. Pal, A. Belaïd, . Ch, and . Choisy, Touching numeral segmentation using water reservoir concept, Pattern Recognition Letters, vol.24, issue.1-3, pp.261-272, 2003.
DOI : 10.1016/S0167-8655(02)00240-4
URL : https://hal.archives-ouvertes.fr/inria-00099525

]. C. Parada, M. Dredze, D. Filimonov, and F. Jelinek, Contextual information improves OOV detection in speech. Human Language Technologies, The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp.216-224, 2010.

]. S. Patwardhan and E. Riloff, Effective Information Extraction with Semantic Affinity Patterns and Relevant Regions, Conference on Empirical Methods in Natural Language Processing, pp.717-727, 2007.

]. F. Perraud, C. Viard-gaudin, E. Morin, and P. Lallican, N-gram and N-class models for on line handwriting recognition, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings., pp.1053-61, 2003.
DOI : 10.1109/ICDAR.2003.1227818
URL : http://www.csc.liv.ac.uk/~prima/ICDAR2003/Papers/0192_605_viard-gaudin_c.pdf

]. M. Pfister, S. Behnke, and R. Rojas, Recognition of Handwritten ZIP Codes in a Real-World Non-Standard-Letter Sorting System, Applied Intelligence, vol.12, issue.1/2, pp.95-115, 2000.
DOI : 10.1023/A:1008316121543

]. R. Plamondon and S. N. Srihari, Online and off-line handwriting recognition: a comprehensive survey, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.22, issue.1, pp.63-84, 2000.
DOI : 10.1109/34.824821

]. E. Poisson, C. Viard-gaudin, and P. M. Lallican, Système TDNN / HMM de reconnaissance de mots cursifs en ligne à apprentissage simplifié. Conférence Internationale Francophone sur l'Ecrit et le Document, pp.48-83, 2004.

]. E. Poisson, Architecture et Apprentissage d'un Système Hybride Neuro-Markovien pour la Reconnaissance de l'Écriture Manuscrite En-Ligne, pp.152-155, 2005.

]. A. Quattoni, S. Wang, L. P. Morency, M. Collins, and T. Darrell, Hidden conditional random fields. Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol.29, issue.10, pp.1848-1852, 2007.
DOI : 10.1109/tpami.2007.1124

]. S. Quiniou, Intégration de connaissances linguistiques pour la reconnaissance de textes manuscrits en-ligne, pp.37-61, 2007.

]. L. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition Readings in speech recognition, pp.267-296, 1990.

]. L. Rabiner and B. Juang, Fundamentals of Speech Recognition, p.90, 1993.

]. M. Ranzato, C. Poultney, S. Chopra, and Y. Lecun, Efficient Learning of Sparse Representations with an Energy-Based Model, NIPS, pp.1137-1144, 2006.

]. T. Rath, S. Kane, A. Lehman, E. Partridge, and R. Manmatha, Indexing for a Digital Library of George Washington's Manuscripts : A Study of Word Matching Techniques, pp.34-57, 2002.

]. T. Bibliographie, R. Rath, and . Manmatha, Features for Word Spotting in Historical Manuscripts, Proc. ICDAR, pp.218-222, 2003.

]. T. Rath, R. Manmatha, and V. Lavrenko, A search engine for historical manuscript images, Proceedings of the 27th annual international conference on Research and development in information retrieval , SIGIR '04, pp.369-376, 2004.
DOI : 10.1145/1008992.1009056
URL : http://works.bepress.com/cgi/viewcontent.cgi?article=1057&context=r_manmatha

]. M. Richard and R. P. Lippmann, Probabilities, Neural Computation, vol.2, issue.11, pp.461-483, 1991.
DOI : 10.1162/neco.1989.1.4.425

]. S. Rifai, Y. N. Dauphin, P. Vincent, Y. Bengio, and X. Muller, The Manifold Tangent Classifier, Advances in Neural Information Processing Systems 24, pp.2294-2302, 2011.

]. S. Rifai, G. Mesnil, P. Vincent, X. Muller, Y. Bengio et al., Higher Order Contractive Auto-Encoder, ECML/PKDD, pp.645-660, 2011.
DOI : 10.1016/S0042-6989(97)00169-7
URL : https://link.springer.com/content/pdf/10.1007%2F978-3-642-23783-6_41.pdf

]. S. Rifai, X. Muller, X. Glorot, G. Mesnil, Y. Bengio et al., Learning invariant features through local space contraction, pp.140-173, 1104.

]. S. Rifai, P. Vincent, X. Muller, X. Glorot, and Y. Bengio, Contractive Auto-Encoders : Explicit Invariance During Feature Extraction, ICML, pp.833-840, 2011.

]. E. Riloff, Automatically Constructing a Dictionary for Information Extraction Tasks, Proceedings of 11th National Conference on Artificial Intelligence, pp.811-816, 1993.

]. E. Riloff, Automatically Generating Extraction Patterns from Untagged Text, Proceedings of 13th National Conference on Artificial Intelligence, pp.1044-1049, 1996.

J. A. Rodríguez-serrano, F. Perronnin, and J. Llados, Score normalization for HMM-based word spotting using a universal background model, p.60, 1924.

]. J. Rodríguez-serrano-2009a, F. Rodríguez-serrano, F. Perronnin, J. Perronnin, and . Llados, Handwritten word-spotting using hidden Markov models and universal vocabularies A similarity measure between vector sequences with application to handwritten word image retrieval, Pattern Recognition, vol.54, issue.56, pp.2106-2116, 1924.

]. J. Rodriguez and F. Perronnin, Local gradient histogram features for word spotting in unconstrained handwritten documents, Proceedings of the 1st International Conference on Handwriting Recognition (ICFHR'08), pp.85-87, 1925.

]. F. Rosenblatt, The perceptron: A probabilistic model for information storage and organization in the brain., Psychological Review, vol.65, issue.6, pp.386-408, 1958.
DOI : 10.1037/h0042519

]. J. Rothfeder, S. Feng, and T. M. Rath, Using Corner Feature Correspondences to Rank Word Images by Similarity, 2003 Conference on Computer Vision and Pattern Recognition Workshop, pp.30-35, 2003.
DOI : 10.1109/CVPRW.2003.10021
URL : http://ciir.cs.umass.edu/pubfiles/mm-44.pdf

]. D. Rumelhart, G. E. Hinton, and R. J. Williams, Learning representations by back-propagating errors, Nature, vol.85, issue.6088, pp.533-536, 1986.
DOI : 10.1038/323533a0

]. J. Sadri, C. Y. Suen, and T. D. Bui, A genetic framework using contextual knowledge for segmentation and recognition of handwritten numeral strings, Pattern Recognition, vol.40, issue.3, pp.898-919, 2007.
DOI : 10.1016/j.patcog.2006.08.002

]. H. Sakoe, Dynamic programming algorithm optimization for spoken word recognition, IEEE Transactions on Acoustics, Speech, and Signal Processing, vol.26, issue.1, pp.43-49, 1978.
DOI : 10.1109/TASSP.1978.1163055

]. A. Sanchis, V. Jimenez, and E. Vidal, Efficient use of the grammar scale factor to classify incorrect words in speech recognition verification, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000, pp.3278-3281, 2000.
DOI : 10.1109/ICPR.2000.903538

]. K. Sankar and C. Jawahar, Probabilistic Reverse Annotation for Large Scale Image Retrieval, 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp.1-6, 2007.
DOI : 10.1109/CVPR.2007.383169
URL : http://cvit.iiit.ac.in/papers/pramodk07Probabilistic.pdf

]. G. Saon and A. Belaïd, Off-line handwritten word recognition using a mixed HMM-MRF approach, Proceedings of the Fourth International Conference on Document Analysis and Recognition, pp.118-122, 1997.
DOI : 10.1109/ICDAR.1997.619825
URL : https://hal.archives-ouvertes.fr/inria-00537568

E. Saykol, A. Sinop, U. Güdükbay, and Ö. , Content-Based Retrieval of Historical Ottoman Documents Stored as Textual Images, IEEE Transactions on Image Processing, vol.13, issue.3, pp.314-325, 2004.
DOI : 10.1109/TIP.2003.821114

]. K. Sayre, Machine recognition of handwritten words: A project report, Pattern Recognition, vol.5, issue.3, pp.213-228, 1973.
DOI : 10.1016/0031-3203(73)90044-7

]. M. Schuster-1997, K. K. Schuster, and . Paliwal, Bidirectional recurrent neural networks, IEEE Transactions on Signal Processing, vol.45, issue.11, pp.2673-2681, 1997.
DOI : 10.1109/78.650093

]. F. Sebastiani, Machine learning in automated text categorization, ACM Computing Surveys, vol.34, issue.1, pp.1-47, 2002.
DOI : 10.1145/505282.505283
URL : http://arxiv.org/pdf/cs/0110053

]. A. Senior and A. J. Robinson, An off-line cursive handwriting recognition system, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.20, issue.3, pp.309-321, 1998.
DOI : 10.1109/34.667887

]. F. Sha and L. K. Saul, Large margin hidden Markov models for automatic speech recognition Advances in neural information processing systems, pp.1249-50, 2007.

]. S. Shetty, H. Srinivasan, and S. Srihari, Handwritten Word Recognition Using Conditional Random Fields, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2, pp.1098-1102, 2007.
DOI : 10.1109/ICDAR.2007.4377085

]. R. Sicard, T. Artières, and E. Petit, Modélisation de l'écrit en ligne à l'aide de réseaux bayésiens et de caractéristiques relationnelles, RFIA, p.50, 2006.

]. S. Srihari and E. J. Kuebert, Integration of hand-written address interpretation technology into the United States Postal Service Remote Computer Reader system, Proceedings of the Fourth International Conference on Document Analysis and Recognition, pp.892-896, 1997.
DOI : 10.1109/ICDAR.1997.620640

]. C. Suen, Q. Xu, and L. Lam, Automatic recognition of handwritten data on cheques ??? Fact or fiction?, Pattern Recognition Letters, vol.20, issue.11-13, pp.11-13, 1999.
DOI : 10.1016/S0167-8655(99)00098-7

]. K. Terasawa, T. Nagasaki, T. Kawashima, E. Trentin, and M. Gori, Eigenspace Method for Text Retrieval in Historical Document Images. ICDAR A survey of hybrid ANN/HMM models for automatic speech recognition, Neurocomputing, vol.57, issue.155, pp.437-441, 2001.

]. O. Trier, A. Jain, and T. Taxt, Feature extraction methods for character recognition-A survey, Pattern Recognition, vol.29, issue.4, pp.641-662, 1996.
DOI : 10.1016/0031-3203(95)00118-2

L. Zant, K. Schomaker, and . Haak, Handwritten-Word Spotting Using Biologically Inspired Features, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.30, issue.11, pp.1945-1957, 2008.
DOI : 10.1109/TPAMI.2008.144

]. V. Vapnik, Statistical Learning Theory, p.140, 1998.

]. P. Vincent, H. Larochelle, Y. Bengio, and P. Manzagol, Extracting and composing robust features with denoising autoencoders, Proceedings of the 25th international conference on Machine learning, ICML '08, pp.1096-1103, 2008.
DOI : 10.1145/1390156.1390294
URL : http://www.iro.umontreal.ca/~vincentp/Publications/denoising_autoencoders_tr1316.pdf

]. P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, and P. Manzagol, Stacked Denoising Autoencoders : Learning Useful Representations in a Deep Network with a Local Denoising Criterion, Journal of Machine Learning Research, vol.11, pp.3371-3408, 2010.

]. A. Vinciarelli-2002 and . Vinciarelli, A survey on off-line Cursive Word Recognition, Pattern Recognition, vol.35, issue.7, pp.1433-1446, 2002.
DOI : 10.1016/S0031-3203(01)00129-7

]. A. Vinciarelli, Offline Cursive Handwriting : From Word to Text Recognition, IDIAP-RR, vol.24, issue.86, pp.85-87, 2003.

A. Vinciarelli, S. Bengio, and H. Bunke, Offline Recognition of Unconstrained Handwritten Texts Using HMMs and Statistical Language Models, IEEE Trans. on PAMI, vol.26, issue.87, pp.709-720, 2004.

]. A. Vinel, T. M. Do, and T. Artières, Neuro HCRFs pour l'étiquetage de signaux. 7e Plateforme AFIA : Association Française pour Bibliographie l'Intelligence Artificielle, p.409, 2011.

]. T. Vintsyuk-1968 and . Vintsyuk, Speech discrimination by dynamic programming, Cybernetics, vol.4, issue.1, pp.81-88, 1968.
DOI : 10.1007/BF01074755

]. A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, and K. J. Lang, Phoneme recognition using time-delay neural networks, IEEE Transactions on Acoustics, Speech, and Signal Processing, vol.37, issue.3, pp.328-339, 1989.
DOI : 10.1109/29.21701

]. C. Weliwitage, A. Harvey, and A. Jennings, Whole of word recognition methods for cursive script, WDIC, vol.39, pp.111-116, 2003.

]. P. Werbos, Beyond Regression : New Tools for Prediction and Analysis in the Behavioral Sciences, p.144, 1974.

]. F. Wessel, R. Schluter, K. Macherey, and H. Ney, Confidence measures for large vocabulary continuous speech recognition. Speech and Audio Processing, IEEE Transactions on, vol.9, issue.3, pp.288-298, 2001.
DOI : 10.1109/89.906002

A. Eyben, B. Graves, and G. Schuller, Bidirectional LSTM networks for context-sensitive keyword detection in a cognitive virtual agent framework, Cognitive Computation, vol.2, issue.3, pp.180-190, 2010.

]. K. Wong, R. G. Casey, and F. M. Wahl, Document Analysis System, IBM Journal of Research and Development, vol.26, issue.6, pp.647-656, 1982.
DOI : 10.1147/rd.266.0647

. C. Woodland-2002-]-p, D. Woodland, and . Povey, Large scale discriminative training of hidden Markov models for speech recognition, Computer Speech & Language, vol.16, issue.1, pp.25-47, 2002.
DOI : 10.1006/csla.2001.0182

]. Q. Xu, L. Lam, and C. Y. Suen, Automatic Segmentation and Recognition System for Handwritten Dates on Canadian Bank Cheques, Proceedings of the Seventh International Conference on Document Analysis and Recognition, pp.704-727, 2003.

]. Xue, D. Xing, Q. Yang, and Y. Yu, Deep classification in largescale text hierarchies, Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval, pp.619-626, 2008.
DOI : 10.1145/1390334.1390440
URL : http://www.cse.ust.hk/~qyang/Docs/2008/fp350-xue.pdf

K. Suen, G. Liu, and . Kim, Extraction of bankcheck items by mathematical morphology, Proceedings of the Seventh International Conference on Document Analysis and Recognition, pp.53-66, 1999.
DOI : 10.1007/s100320050037

]. S. Young, N. H. Russell, and J. H. Thornton, Token Passing : a Simple Conceptual Model for Connected Speech Recognition Systems, Mathematics of Control, Signals, and Systems (MCSS), pp.1-8, 1989.

T. Zeppenfeld, M. Finke, K. Ries, M. Westphal, and A. Waibel, Recognition of conversational telephone speech using the JANUS speech engine, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, pp.1815-1818, 1997.
DOI : 10.1109/ICASSP.1997.598889

]. Y. Zheng, H. Li, and D. Doermann, A parallel-line detection algorithm based on HMM decoding, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.27, issue.5, pp.777-792, 2005.
DOI : 10.1109/TPAMI.2005.89

]. M. Zimmermann and H. Bunke, Parsing n-best lists of handwritten sentences. ICDAR, pp.572-576, 2003.

]. M. Zimmermann, R. Bertolami, and H. Bunke, Rejection strategies for offline handwritten sentence recognition, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., pp.550-553, 2004.
DOI : 10.1109/ICPR.2004.1334301
URL : http://www.iam.unibe.ch/~bertolam/publications/rejection_icpr_2004.pdf

]. M. Zimmermann and H. Bunke, Optimizing the Integration of a Statistical Language Model in HMM based Offine Handwritten Text Recognition, ICPR, vol.54, issue.2, pp.541-544, 2004.

]. M. Zimmermann and J. Chappelier, Offline grammar-based recognition of handwritten sentences, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.28, issue.5, pp.818-821, 2006.
DOI : 10.1109/TPAMI.2006.103

S. Thomas, C. Chatelain, L. Heutte, and T. Paquet, Alpha-Numerical Sequences Extraction in Handwritten Documents, 2010 12th International Conference on Frontiers in Handwriting Recognition, pp.232-237, 2010.
DOI : 10.1109/ICFHR.2010.44
URL : https://hal.archives-ouvertes.fr/hal-00488290

S. Thomas, C. Chatelain, L. Heutte, and T. Paquet, An Information Extraction Model for Unconstrained Handwritten Documents, 2010 20th International Conference on Pattern Recognition, p.4, 2010.
DOI : 10.1109/ICPR.2010.833
URL : https://hal.archives-ouvertes.fr/hal-00486107

S. Thomas, C. Chatelain, L. Heutte, and T. Paquet, Un mod??le neuro markovien profond pour l???extraction de s??quences dans des documents manuscrits, Document num??rique, vol.16, issue.2, 2012.
DOI : 10.3166/dn.16.2.49-68

S. Thomas, C. Chatelain, L. Heutte, and T. Paquet, Combinaison architecture profonde/hmm pour l'extraction de sequences dans des documents manuscrits, Cifed, 2012.
DOI : 10.3166/dn.16.2.49-68

S. Thomas, C. Chatelain, L. Heutte, and T. Paquet, Un systeme generique d'extraction d'information dans des documents manuscrits non-contraints, Cifed, 2010.
URL : https://hal.archives-ouvertes.fr/hal-00488277