2012
|
del Agua, MiguelA.; Serrano, Nicolás ; Civera, Jorge ; Juan, Alfons Character-Based Handwritten Text Recognition of Multilingual Documents Incollection Advances in Speech and Language Technologies for Iberian Languages (IberSpeech 2012), 328 , pp. 187-196, Springer Berlin Heidelberg, 2012, ISBN: 978-3-642-35291-1, (doi: 10.1007/978-3-642-35292-8_20). Links | BibTeX | Tags: @incollection{delAgua12,
title = {Character-Based Handwritten Text Recognition of Multilingual Documents},
author = {MiguelA. del Agua and Nicolás Serrano and Jorge Civera and Alfons Juan},
url = {http://hdl.handle.net/10251/35180},
isbn = {978-3-642-35291-1},
year = {2012},
date = {2012-01-01},
booktitle = {Advances in Speech and Language Technologies for Iberian Languages (IberSpeech 2012)},
volume = {328},
pages = {187-196},
publisher = {Springer Berlin Heidelberg},
series = {Communications in Computer and Information Science},
note = {doi: 10.1007/978-3-642-35292-8_20},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
|
Gascó, Guillem; Rocha, Martha-Alicia ; Sanchis-Trilles, Germán ; Andrés-Ferrer, Jesús ; Casacuberta, Francisco Does more data always yield better translations? Inproceedings Proc. of the 13th Conf. of the European Chapter of the Association for Computational Linguistics (EACL 2012), pp. 152–161, Association for Computational Linguistics, Avignon (France), 2012. Links | BibTeX | Tags: @inproceedings{gasco-EtAl:2012:EACL2012,
title = {Does more data always yield better translations?},
author = { Guillem Gascó and Martha-Alicia Rocha and Germán Sanchis-Trilles and Jesús Andrés-Ferrer and Francisco Casacuberta},
url = {http://hdl.handle.net/10251/35214},
year = {2012},
date = {2012-01-01},
booktitle = {Proc. of the 13th Conf. of the European Chapter of the Association for Computational Linguistics (EACL 2012)},
pages = {152--161},
publisher = {Association for Computational Linguistics},
address = {Avignon (France)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Doetsch, Patrick; Hamdani, Mahdi; Giménez-Pastor, Adrià; Andrés-Ferrer, Jesús; Juan, Alfons; Ney, Hermann Comparison of Bernoulli and Gaussian HMMs using a vertical repositioning technique for off-line handwriting recognition Inproceedings Proc. of the 2012 Intl. Conf. on Frontiers in Handwriting Recognition (ICFHR 2012), pp. 3 – 7, 2012. BibTeX | Tags: @inproceedings{doetsch12,
title = {Comparison of Bernoulli and Gaussian HMMs using a vertical repositioning technique for off-line handwriting recognition},
author = {Patrick Doetsch and Mahdi Hamdani and Adrià Giménez-Pastor and Jesús Andrés-Ferrer and Alfons Juan and Hermann Ney},
year = {2012},
date = {2012-01-01},
booktitle = {Proc. of the 2012 Intl. Conf. on Frontiers in Handwriting Recognition (ICFHR 2012)},
pages = {3 -- 7},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Khoury, Ihab; Giménez-Pastor, Adrià; Juan, Alfons Guide to OCR for Arabic Scripts Book Chapter Märgner Volkerand El Abed, Haikal (Ed.): Chapter Arabic Handwriting Recognition Using Ber, pp. 255-272, Springer, 2012. BibTeX | Tags: @inbook{Khoury12-AHRBook-chp10,
title = {Guide to OCR for Arabic Scripts},
author = {Ihab Khoury and Adrià Giménez-Pastor and Alfons Juan},
editor = {Märgner, Volkerand El Abed, Haikal },
year = {2012},
date = {2012-01-01},
pages = {255-272},
publisher = {Springer},
chapter = {Arabic Handwriting Recognition Using Ber},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
|
González-Rubio, Jesús; Sanchis, Alberto; Casacuberta, Francisco PRHLT Submission to the WMT12 Quality Estimation Task Inproceedings Proceedings of the Seventh Workshop on Statistical Machine Translation, pp. 104–108, North American Chapter of the Association for Computational Linguistics Association for Computational Linguistics, 2012. BibTeX | Tags: @inproceedings{gonzalezrubio2012b,
title = {PRHLT Submission to the WMT12 Quality Estimation Task},
author = {Jesús González-Rubio and Alberto Sanchis and Francisco Casacuberta},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of the Seventh Workshop on Statistical Machine Translation},
pages = {104--108},
publisher = {Association for Computational Linguistics},
organization = {North American Chapter of the Association for Computational Linguistics},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Ortiz-Martínez, Daniel; Sanchis-Trilles, Germán; Casacuberta, Francisco; Alabau, Vicent; Vidal, Enrique; Benedí, José-Miguel; González-Rubio, Jesús; Sanchis, Alberto; González, Jorge The CASMACAT Project: The Next Generation Translator’s Workbench Inproceedings Proceedings of IberSPEECH 2012, pp. 326-334, Madrid (Spain), 2012. BibTeX | Tags: @inproceedings{Ortiz-Martínez2012,
title = {The CASMACAT Project: The Next Generation Translator’s Workbench},
author = {Daniel Ortiz-Martínez and Germán Sanchis-Trilles and Francisco Casacuberta and Vicent Alabau and Enrique Vidal and José-Miguel Benedí and Jesús González-Rubio and Alberto Sanchis and Jorge González},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of IberSPEECH 2012},
pages = {326-334},
address = {Madrid (Spain)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Valor Miró, Juan Daniel ; Pérez González de Martos, Alejandro ; Civera, Jorge ; Juan, Alfons Integrating a State-of-the-Art ASR System into the Opencast Matterhorn Platform Incollection Advances in Speech and Language Technologies for Iberian Languages (IberSpeech 2012), 328 , pp. 237-246, Springer Berlin Heidelberg, 2012, ISBN: 978-3-642-35291-1, (doi: 10.1007/978-3-642-35292-8_20). Links | BibTeX | Tags: Google N-Gram, Language Modeling, Linear Combination, Opencast Matterhorn, Speech Recognition @incollection{Valor2012,
title = {Integrating a State-of-the-Art ASR System into the Opencast Matterhorn Platform},
author = {Valor Miró, Juan Daniel and Pérez González de Martos, Alejandro and Civera, Jorge and Juan, Alfons},
url = {http://hdl.handle.net/10251/35190
http://www.mllp.upv.es/wp-content/uploads/2015/04/paper2.pdf},
isbn = {978-3-642-35291-1},
year = {2012},
date = {2012-01-01},
booktitle = {Advances in Speech and Language Technologies for Iberian Languages (IberSpeech 2012)},
volume = {328},
pages = {237-246},
publisher = {Springer Berlin Heidelberg},
series = {Communications in Computer and Information Science},
note = {doi: 10.1007/978-3-642-35292-8_20},
keywords = {Google N-Gram, Language Modeling, Linear Combination, Opencast Matterhorn, Speech Recognition},
pubstate = {published},
tppubtype = {incollection}
}
|
Silvestre-Cerdà, Joan Albert; Andrés-Ferrer, Jesús; Civera, Jorge Explicit length modelling for statistical machine translation Journal Article Pattern Recognition, 45 (9), pp. 3183 - 3192, 2012, ISSN: 0031-3203. Abstract | Links | BibTeX | Tags: Length modelling, Log-linear models, Phrase-based models, Statistical machine translation @article{Silvestre-Cerdà2012a,
title = {Explicit length modelling for statistical machine translation},
author = {Joan Albert Silvestre-Cerdà and Jesús Andrés-Ferrer and Jorge Civera},
url = {http://hdl.handle.net/10251/34996},
issn = {0031-3203},
year = {2012},
date = {2012-01-01},
journal = {Pattern Recognition},
volume = {45},
number = {9},
pages = {3183 - 3192},
abstract = {Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods and two alternative parametrisation for statistical machine translation (SMT) are presented. More precisely, we incorporate explicit bilingual length modelling in a state-of-the-art log-linear SMT system as an additional feature function in order to prove the contribution of length information. Finally, a systematic evaluation on reference SMT tasks considering different language pairs prove the benefits of explicit length modelling.},
keywords = {Length modelling, Log-linear models, Phrase-based models, Statistical machine translation},
pubstate = {published},
tppubtype = {article}
}
Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods and two alternative parametrisation for statistical machine translation (SMT) are presented. More precisely, we incorporate explicit bilingual length modelling in a state-of-the-art log-linear SMT system as an additional feature function in order to prove the contribution of length information. Finally, a systematic evaluation on reference SMT tasks considering different language pairs prove the benefits of explicit length modelling. |
2011
|
Silvestre-Cerdà, Joan Albert Modelat explícit de la longitud en Traducció Automàtica Estadística Masters Thesis Màster U. en Intel·ligència Artificial, Reconeixement de Formes i Imatge Digital, Universitat Politècnica de València, 2011. Abstract | Links | BibTeX | Tags: Modelat de la longitud, Models basats en seqüències de paraules, Models log-lineals, Traducció Automàtica Estadística @mastersthesis{Silvestre-Cerdà2011b,
title = {Modelat explícit de la longitud en Traducció Automàtica Estadística},
author = {Joan Albert Silvestre-Cerdà},
url = {http://www.mllp.upv.es/wp-content/uploads/2014/04/memoria2.pdf},
year = {2011},
date = {2011-09-08},
school = {Màster U. en Intel·ligència Artificial, Reconeixement de Formes i Imatge Digital, Universitat Politècnica de València},
abstract = {El modelat explícit de la longitud és un problema que ha estat explorat prèviament en diferents tasques de reconeixement de formes, oferint bons resultats. En aquest treball, es presenten dos models de longitud juntament amb dos mètodes d\'estimació i dos parametritzacions alternatives per a traducció automàtica estadística (TAE). Concretament, hem incorporat els models de longitud com a característiques addicionals al model logarítmic-lineal d\'un sistema de TAE estat de l\'art basat en seqüències de paraules, amb l\'objectiu d\'estudiar la contribució de la informació de la longitud de les seqüències de paraules en el procés de traducció. Es mostren els resultats dels experiments que hem dut a terme en una tasca de referència de la TAE, els quals posen en relleu els beneficis del modelat explícit de la longitud.},
keywords = {Modelat de la longitud, Models basats en seqüències de paraules, Models log-lineals, Traducció Automàtica Estadística},
pubstate = {published},
tppubtype = {mastersthesis}
}
El modelat explícit de la longitud és un problema que ha estat explorat prèviament en diferents tasques de reconeixement de formes, oferint bons resultats. En aquest treball, es presenten dos models de longitud juntament amb dos mètodes d'estimació i dos parametritzacions alternatives per a traducció automàtica estadística (TAE). Concretament, hem incorporat els models de longitud com a característiques addicionals al model logarítmic-lineal d'un sistema de TAE estat de l'art basat en seqüències de paraules, amb l'objectiu d'estudiar la contribució de la informació de la longitud de les seqüències de paraules en el procés de traducció. Es mostren els resultats dels experiments que hem dut a terme en una tasca de referència de la TAE, els quals posen en relleu els beneficis del modelat explícit de la longitud. |
del Agua, MiguelA. ; Serrano, Nicolás ; Juan, Alfons Language Identification for Interactive Handwriting Transcription of Multilingual Documents Incollection Pattern Recognition and Image Analysis (IbPRIA 2011), 6669 , pp. 596-603, Springer Berlin Heidelberg, 2011, ISBN: 978-3-642-21256-7. Links | BibTeX | Tags: interactive handwriting transcription, Language identification, Multilingual documents @incollection{delAgua2011b,
title = {Language Identification for Interactive Handwriting Transcription of Multilingual Documents},
author = {del Agua, MiguelA. and Serrano, Nicolás and Juan, Alfons},
url = {http://hdl.handle.net/10251/37459
http://dx.doi.org/10.1007/978-3-642-21257-4_74},
isbn = {978-3-642-21256-7},
year = {2011},
date = {2011-01-01},
booktitle = {Pattern Recognition and Image Analysis (IbPRIA 2011)},
volume = {6669},
pages = {596-603},
publisher = {Springer Berlin Heidelberg},
series = {Lecture Notes in Computer Science},
keywords = {interactive handwriting transcription, Language identification, Multilingual documents},
pubstate = {published},
tppubtype = {incollection}
}
|
Romero, Verónica; Serrano, Nicolás; Toselli, Alejandro H; Sánchez, Joan-Andreu; Vidal, Enrique Handwritten Text Recognition for Historical Documents Inproceedings Proc. of the Workshop on Language Technologies for Digital Humanities and Cultural Heritage (RANLP 2011), pp. 90–96, Hissar (Bulgaria), 2011. BibTeX | Tags: @inproceedings{Romero11b,
title = {Handwritten Text Recognition for Historical Documents},
author = {Verónica Romero and Nicolás Serrano and Alejandro H. Toselli and Joan-Andreu Sánchez and Enrique Vidal},
year = {2011},
date = {2011-01-01},
booktitle = {Proc. of the Workshop on Language Technologies for Digital Humanities and Cultural Heritage (RANLP 2011)},
pages = {90--96},
address = {Hissar (Bulgaria)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Romero, Verónica; Sánchez, Joan-Andreu; Serrano, Nicolás; Vidal, Enrique Handwritten Text Recognition for Marriage Register Books Inproceedings Proceedings of the International Conference on Document Analysis and Recognition (ICDAR 2011), pp. 533-537, IEEE Computer Society, 2011. BibTeX | Tags: @inproceedings{Romero11a,
title = {Handwritten Text Recognition for Marriage Register Books},
author = {Verónica Romero and Joan-Andreu Sánchez and Nicolás Serrano and Enrique Vidal},
year = {2011},
date = {2011-01-01},
booktitle = {Proceedings of the International Conference on Document Analysis and Recognition (ICDAR 2011)},
pages = {533-537},
publisher = {IEEE Computer Society},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Leiva, Luis A; Alabau, Vicent; Romero, Verónica; Segarra, Franco M; Sánchez-Sáez, Ricardo; Ortiz-Martínez, Daniel; Rodríguez-Ruiz, Luis; Serrano, Nicolás Multimodal Interactive Pattern Recognition and Applications Book Chapter Toselli, Alejandro H; Vidal, Enrique; Casacuberta, Francisco (Ed.): Chapter Prototypes and Demonstrators, Springer, 1st Edition, 2011, (http://www.springer.com/computer/hci/book/978-0-85729-478-4). BibTeX | Tags: @inbook{Leiva11-mipra-chp12,
title = {Multimodal Interactive Pattern Recognition and Applications},
author = {Luis A. Leiva and Vicent Alabau and Verónica Romero and Franco M. Segarra and Ricardo Sánchez-Sáez and Daniel Ortiz-Martínez and Luis Rodríguez-Ruiz and Nicolás Serrano},
editor = {Alejandro H. Toselli and Enrique Vidal and Francisco Casacuberta},
year = {2011},
date = {2011-01-01},
publisher = {Springer},
edition = {1st Edition},
chapter = {Prototypes and Demonstrators},
note = {http://www.springer.com/computer/hci/book/978-0-85729-478-4},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
|
Serrano, Nicolás; Giménez-Pastor, Adrià; Sanchis, Alberto; Juan, Alfons Multimodal Interactive Pattern Recognition and Applications Book Chapter Toselli, Alejandro H; Vidal, Enrique; Casacuberta, Francisco (Ed.): Chapter Active Interaction and Learning in Handw, Springer, 1st Edition, 2011, (http://www.springer.com/computer/hci/book/978-0-85729-478-4). BibTeX | Tags: @inbook{Serrano11-mipra-chp05,
title = {Multimodal Interactive Pattern Recognition and Applications},
author = {Nicolás Serrano and Adrià Giménez-Pastor and Alberto Sanchis and Alfons Juan},
editor = {Alejandro H. Toselli and Enrique Vidal and Francisco Casacuberta},
year = {2011},
date = {2011-01-01},
publisher = {Springer},
edition = {1st Edition},
chapter = {Active Interaction and Learning in Handw},
note = {http://www.springer.com/computer/hci/book/978-0-85729-478-4},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
|
Serrano, Nicolás Multiple Contributions to Interactive Transcription and Translation of Old Text Documents Masters Thesis Master's Degree in Artificial Intelligence, Pattern Recognition and Digital Imaging, Universitat Politècnica de València, 2011. Links | BibTeX | Tags: @mastersthesis{Serrano11a,
title = {Multiple Contributions to Interactive Transcription and Translation of Old Text Documents},
author = {Nicolás Serrano},
url = {http://hdl.handle.net/10251/11272},
year = {2011},
date = {2011-01-01},
school = {Master's Degree in Artificial Intelligence, Pattern Recognition and Digital Imaging, Universitat Politècnica de València},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
|
Andrés-Ferrer, Jesús; Romero, Verónica; Sanchis, Alberto Multimodal Interactive Pattern Recognition and Applications Book Chapter Toselli, Alejandro H; Vidal, Enrique; Casacuberta, Francisco (Ed.): Chapter General Framework, Springer, 1st Edition, 2011. BibTeX | Tags: @inbook{Andres11-mipra-chp01,
title = {Multimodal Interactive Pattern Recognition and Applications},
author = {Jesús Andrés-Ferrer and Verónica Romero and Alberto Sanchis},
editor = {Alejandro H. Toselli and Enrique Vidal and Francisco Casacuberta},
year = {2011},
date = {2011-01-01},
publisher = {Springer},
edition = {1st Edition},
chapter = {General Framework},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
|
Alabau, Vicent; Sanchis, Alberto; Casacuberta, Francisco Improving On-line Handwritten Recognition using Translation Models in Multimodal Interactive Machine Translation Inproceedings Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 389–394, Association for Computational Linguistics, 2011. BibTeX | Tags: @inproceedings{alabau-sanchis-casacuberta:2011:ACL-HLT2011,
title = {Improving On-line Handwritten Recognition using Translation Models in Multimodal Interactive Machine Translation},
author = {Vicent Alabau and Alberto Sanchis and Francisco Casacuberta},
year = {2011},
date = {2011-01-01},
booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies},
pages = {389--394},
publisher = {Association for Computational Linguistics},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Alabau, Vicent; Rodríguez-Ruiz, Luis; Sanchis, Alberto; Martínez-Gómez, Pascual; Casacuberta, Francisco On multimodal interactive machine translation using speech recognition Inproceedings Proc. of the Intl. Conf. on Multimodal Interaction - ICMI'11, pp. 129–136, 2011. BibTeX | Tags: @inproceedings{valabau11c,
title = {On multimodal interactive machine translation using speech recognition},
author = {Vicent Alabau and Luis Rodríguez-Ruiz and Alberto Sanchis and Pascual Martínez-Gómez and Francisco Casacuberta},
year = {2011},
date = {2011-01-01},
booktitle = {Proc. of the Intl. Conf. on Multimodal Interaction - ICMI'11},
pages = {129--136},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Giménez-Pastor, Adrià; Andrés-Ferrer, Jesús; Juan, Alfons; Serrano, Nicolás Discriminative Bernoulli Mixture Models for Handwritten Digit Recognition Inproceedings Proc. of the 11th International Conference on Document Analysis and Recognition ICDAR 2011, pp. 558 – 562, IEEE Computer Society Conference Publishing Services, 2011. BibTeX | Tags: @inproceedings{gimenez11,
title = {Discriminative Bernoulli Mixture Models for Handwritten Digit Recognition},
author = {Adrià Giménez-Pastor and Jesús Andrés-Ferrer and Alfons Juan and Nicolás Serrano},
year = {2011},
date = {2011-01-01},
booktitle = {Proc. of the 11th International Conference on Document Analysis and Recognition ICDAR 2011},
pages = {558 -- 562},
publisher = {IEEE Computer Society Conference Publishing Services},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Silvestre-Cerdà, Joan Albert; Andrés-Ferrer, Jesús ; Civera, Jorge Explicit Length Modelling for Statistical Machine Translation Incollection Vitrià, Jordi ; Sanches, JoãoMiguel ; Hernández, Mario (Ed.): Pattern Recognition and Image Analysis (IbPRIA 2011), 6669 , pp. 273-280, Springer Berlin Heidelberg, 2011, ISBN: 978-3-642-21256-7. Abstract | Links | BibTeX | Tags: Length modelling, Log-linear models, Phrase-based models, Statistical machine translation @incollection{Silvestre-Cerdà2011,
title = {Explicit Length Modelling for Statistical Machine Translation},
author = { Joan Albert Silvestre-Cerdà and Jesús Andrés-Ferrer and Jorge Civera},
editor = {Vitrià, Jordi and Sanches, JoãoMiguel and Hernández, Mario},
url = {http://hdl.handle.net/10251/35749
http://dx.doi.org/10.1007/978-3-642-21257-4_34},
isbn = {978-3-642-21256-7},
year = {2011},
date = {2011-01-01},
booktitle = {Pattern Recognition and Image Analysis (IbPRIA 2011)},
volume = {6669},
pages = {273-280},
publisher = {Springer Berlin Heidelberg},
series = {Lecture Notes in Computer Science},
abstract = {Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods for statistical machine translation (SMT) are presented. More precisely, we incorporate explicit length modelling in a state-of-the-art log-linear SMT system as an additional feature function in order to prove the contribution of length information. Finally, promising experimental results are reported on a reference SMT task.},
keywords = {Length modelling, Log-linear models, Phrase-based models, Statistical machine translation},
pubstate = {published},
tppubtype = {incollection}
}
Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods for statistical machine translation (SMT) are presented. More precisely, we incorporate explicit length modelling in a state-of-the-art log-linear SMT system as an additional feature function in order to prove the contribution of length information. Finally, promising experimental results are reported on a reference SMT task. |
Silvestre-Cerdà, Joan Albert; García-Martínez, Mercedes; Barrón-Cedeño, Alberto; Civera, Jorge; Rosso, Paolo Extracción de corpus paralelos de la Wikipedia basada en la obtención de alineamientos bilingües a nivel de frase Inproceedings Proceedings of the Workshop on Iberian Cross-Language Natural Language Processing Tasks (ICL 2011), pp. 14-21, CEUR-WS, 2011, ISSN: 1613-0073. Abstract | Links | BibTeX | Tags: Comparable Corpora, Parallel Sentences Extraction, Statistical machine translation @inproceedings{Silvestre-Cerdà2011b,
title = {Extracción de corpus paralelos de la Wikipedia basada en la obtención de alineamientos bilingües a nivel de frase},
author = {Joan Albert Silvestre-Cerdà and Mercedes García-Martínez and Alberto Barrón-Cedeño and Jorge Civera and Paolo Rosso},
url = {http://hdl.handle.net/10251/27930},
issn = {1613-0073},
year = {2011},
date = {2011-01-01},
booktitle = {Proceedings of the Workshop on Iberian Cross-Language Natural Language Processing Tasks (ICL 2011)},
volume = {824},
pages = {14-21},
publisher = {CEUR-WS},
abstract = {This paper presents a proposal for extracting parallel corpora from Wikipedia on the basis of statistical machine translation techniques. We have used word-level alignment models from IBM in order to obtain phrase-level bilingual alignments between documents pairs. We have manually annotated a set of test English-Spanish comparable documents in order to evaluate the model. The obtained results are encouraging.},
keywords = {Comparable Corpora, Parallel Sentences Extraction, Statistical machine translation},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper presents a proposal for extracting parallel corpora from Wikipedia on the basis of statistical machine translation techniques. We have used word-level alignment models from IBM in order to obtain phrase-level bilingual alignments between documents pairs. We have manually annotated a set of test English-Spanish comparable documents in order to evaluate the model. The obtained results are encouraging. |
González-Rubio, Jesús; Juan, Alfons; Casacuberta, Francisco Minimum Bayes-risk System Combination Inproceedings Proc. of the Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT 2011), pp. 1268-1277, Portland (USA), 2011, (CORE A*: CORE2014, CORE2013, CORE2008 (CORE A: ERA2010)). BibTeX | Tags: @inproceedings{González-Rubio2011,
title = {Minimum Bayes-risk System Combination},
author = {Jesús González-Rubio and Alfons Juan and Francisco Casacuberta},
year = {2011},
date = {2011-01-01},
booktitle = {Proc. of the Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT 2011)},
pages = {1268-1277},
address = {Portland (USA)},
note = {CORE A*: CORE2014, CORE2013, CORE2008 (CORE A: ERA2010)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2010
|
Silvestre-Cerdà, Joan Albert Aportacions a la millora d'un sistema interactiu d'ajuda a la traducció basat en mètodes estadístics Miscellaneous Final Year Project (Computer Science and Engineering at Universitat Politècnica de València), 2010. Links | BibTeX | Tags: Modelat de la longitud, Models basats en seqüències de paraules, Models log-lineals, Traducció Automàtica Estadística @misc{Silvestre-Cerdà2010,
title = {Aportacions a la millora d\'un sistema interactiu d\'ajuda a la traducció basat en mètodes estadístics},
author = {Joan Albert Silvestre-Cerdà},
url = {http://hdl.handle.net/10251/9109
http://www.mllp.upv.es/wp-content/uploads/2014/04/memoria3.pdf},
year = {2010},
date = {2010-11-01},
school = {School of Computer Science, Universitat Politècnica de València},
howpublished = {Final Year Project (Computer Science and Engineering at Universitat Politècnica de València)},
keywords = {Modelat de la longitud, Models basats en seqüències de paraules, Models log-lineals, Traducció Automàtica Estadística},
pubstate = {published},
tppubtype = {misc}
}
|
Andrés Ferrer, Jesús Statistical approaches for natural language modelling and monotone statistical machine translation PhD Thesis Universitat Politècnica de València, 2010, (Advisors: Alfons Juan Ciscar and Francisco Casacuberta Nolla). Links | BibTeX | Tags: @phdthesis{Ferrer2010,
title = {Statistical approaches for natural language modelling and monotone statistical machine translation},
author = {Andrés Ferrer, Jesús},
url = {http://hdl.handle.net/10251/7109},
year = {2010},
date = {2010-02-05},
school = {Universitat Politècnica de València},
note = {Advisors: Alfons Juan Ciscar and Francisco Casacuberta Nolla},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
|
Ramos-Terrades, O; Serrano, N; Gordó, A; Valveny, E; Juan, A Interactive-predictive detection of handwritten text blocks Inproceedings Proc. of SPIE-IS&T Electronic Imaging (SPIE 7534), Document Recognition and Retrieval XVII, pp. 75340Q-(1–10), San Jose, CA (USA), 2010. Abstract | Links | BibTeX | Tags: @inproceedings{Juan10_01,
title = {Interactive-predictive detection of handwritten text blocks},
author = {O. Ramos-Terrades and N. Serrano and A. Gordó and E. Valveny and A. Juan},
url = {http://dx.doi.org/10.1117/12.839665},
year = {2010},
date = {2010-01-01},
booktitle = {Proc. of SPIE-IS&T Electronic Imaging (SPIE 7534), Document Recognition and Retrieval XVII},
pages = {75340Q-(1--10)},
address = {San Jose, CA (USA)},
abstract = {A method for text block detection is introduced for old handwritten documents. The proposed method takes advantage of sequential book structure, taking into account layout information from pages previously transcribed. This glance at the past is used to predict the position of text blocks in the current page with the help of conventional layout analysis methods. The method is integrated into the GIDOC prototype: a first attempt to provide integrated support for interactive-predictive page layout analysis, text line detection and handwritten text transcription. Results are given in a transcription task on a 764-page Spanish manuscript from 1891.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
A method for text block detection is introduced for old handwritten documents. The proposed method takes advantage of sequential book structure, taking into account layout information from pages previously transcribed. This glance at the past is used to predict the position of text blocks in the current page with the help of conventional layout analysis methods. The method is integrated into the GIDOC prototype: a first attempt to provide integrated support for interactive-predictive page layout analysis, text line detection and handwritten text transcription. Results are given in a transcription task on a 764-page Spanish manuscript from 1891. |
Serrano, Nicolás; Sanchis, Albert; Juan, Alfons Balancing Error and Supervision Effort in Interactive-Predictive Handwriting Recognition Inproceedings Proc. of the 14th Int. Conf. on Intelligent User Interfaces (IUI 2010), pp. 373–376, Hong Kong (China), 2010. BibTeX | Tags: @inproceedings{Juan10_02,
title = {Balancing Error and Supervision Effort in Interactive-Predictive Handwriting Recognition},
author = {Nicolás Serrano and Albert Sanchis and Alfons Juan},
year = {2010},
date = {2010-01-01},
booktitle = {Proc. of the 14th Int. Conf. on Intelligent User Interfaces (IUI 2010)},
pages = {373--376},
address = {Hong Kong (China)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Khoury, Ihab; Giménez, Adrià; Juan, Alfons Arabic Handwritten Word Recognition Using Bernoulli Mixture HMMs Inproceedings Proc. of the 3rd Palestinian Int. Conf. on Computer and Information Technology (PICCIT 2010), Hebron (Palestine), 2010. BibTeX | Tags: @inproceedings{Juan10_03a,
title = {Arabic Handwritten Word Recognition Using Bernoulli Mixture HMMs},
author = {Ihab Khoury and Adrià Giménez and Alfons Juan},
year = {2010},
date = {2010-01-01},
booktitle = {Proc. of the 3rd Palestinian Int. Conf. on Computer and Information Technology (PICCIT 2010)},
address = {Hebron (Palestine)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Andres-Ferrer, Jesus; Juan, Alfons Constrained domain maximum likelihood estimation for naive Bayes text classification Journal Article Pattern Analysis and Applications, 13 , pp. 189–196, 2010. BibTeX | Tags: @article{Juan10_04,
title = {Constrained domain maximum likelihood estimation for naive Bayes text classification},
author = {Jesus Andres-Ferrer and Alfons Juan},
year = {2010},
date = {2010-01-01},
journal = {Pattern Analysis and Applications},
volume = {13},
pages = {189--196},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Serrano, N; Castro, F; Juan, A The RODRIGO database Inproceedings Proc. of the 7th Language Resources and Evaluation Conf. (LREC 2010), pp. 2709–2712, Valleta (Malta), 2010. BibTeX | Tags: @inproceedings{Juan10_05a,
title = {The RODRIGO database},
author = {N. Serrano and F. Castro and A. Juan},
year = {2010},
date = {2010-01-01},
booktitle = {Proc. of the 7th Language Resources and Evaluation Conf. (LREC 2010)},
pages = {2709--2712},
address = {Valleta (Malta)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
González-Rubio, J; Civera, J; Juan, A; Casacuberta, F Saturnalia: A Latin-Catalan Parallel Corpus for Statistical MT Inproceedings Proc. of the 7th Language Resources and Evaluation Conf. (LREC 2010), pp. 3405–3408, Valleta (Malta), 2010. BibTeX | Tags: @inproceedings{Juan10_05b,
title = {Saturnalia: A Latin-Catalan Parallel Corpus for Statistical MT},
author = {J. González-Rubio and J. Civera and A. Juan and F. Casacuberta},
year = {2010},
date = {2010-01-01},
booktitle = {Proc. of the 7th Language Resources and Evaluation Conf. (LREC 2010)},
pages = {3405--3408},
address = {Valleta (Malta)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
