Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Nihel Kooli"'
Publikováno v:
International Journal of Data Science and Analytics
International Journal of Data Science and Analytics, Springer Verlag, 2021, 11 (2), pp.85-103. ⟨10.1007/s41060-021-00242-8⟩
International Journal of Data Science and Analytics, 2021, 11 (2), pp.85-103. ⟨10.1007/s41060-021-00242-8⟩
International Journal of Data Science and Analytics, Springer Verlag, 2021, 11 (2), pp.85-103. ⟨10.1007/s41060-021-00242-8⟩
International Journal of Data Science and Analytics, 2021, 11 (2), pp.85-103. ⟨10.1007/s41060-021-00242-8⟩
International audience; Word Embeddings have proven to be effective for many Natural Language Processing tasks by providing word representations integrating prior knowledge. In this article, we focus on the algorithms and models used to compute those
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7301a886ce62d3f070714a5e1991cf1b
https://hal.archives-ouvertes.fr/hal-03148517/document
https://hal.archives-ouvertes.fr/hal-03148517/document
Publikováno v:
Communications in Computer and Information Science ISBN: 9783030368074
ICONIP (4)
ICONIP (4)
Training deep networks requires large volumes of data. However, for many companies developing new products, those data may not be available and public data-sets may not be adapted to their particular use-case. In this paper, we explain how we achieve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::181b61cee5ead07f2565cbf12fa53bea
https://doi.org/10.1007/978-3-030-36808-1_27
https://doi.org/10.1007/978-3-030-36808-1_27
Publikováno v:
Intelligent Information and Database Systems ISBN: 9783319754192
ACIIDS (2)
ACIIDS
ACIIDS, 2, pp.3-12, 2018
ACIIDS (2)
ACIIDS
ACIIDS, 2, pp.3-12, 2018
This paper proposes a Deep Neural Networks (DNN) based approach for entity resolution in databases. This approach is mainly based on a record linkage process which aims to detect records that refer to the same entity. First, record pairs are represen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71e935e1aa11e0c188fe5f97ae6c400f
https://doi.org/10.1007/978-3-319-75420-8_1
https://doi.org/10.1007/978-3-319-75420-8_1
Publikováno v:
ASAR
We present in this paper an approach for handwritten Arabic words recognition. A bi-dimensional model is created by coupling two Hidden Markov Models (HMM) using dynamic Bayesian network formalism. The image of the handwritten word is scanned in orde
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e71d179764e7f38140c038a852aa656a
https://doi.org/10.1109/asar.2017.8067769
https://doi.org/10.1109/asar.2017.8067769
Publikováno v:
DAS
Document Analysis Systems
Document Analysis Systems, Apr 2016, Santorini, Greece. pp.257-262, ⟨10.1109/DAS.2016.36⟩
Document Analysis Systems
Document Analysis Systems, Apr 2016, Santorini, Greece. pp.257-262, ⟨10.1109/DAS.2016.36⟩
International audience; This paper proposes an entity local structure comparison approach based on inexact subgraph matching. The comparison results are used for mislabeling correction in the local structure. The latter represents a set of entity att
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::71d859fd11387c5f7ac3d4acda805076
https://doi.org/10.1109/das.2016.36
https://doi.org/10.1109/das.2016.36
Autor:
Nihel Kooli, Abdel Belaïd
Publikováno v:
ICDAR
13th International Conference on Document Analysis and Recognition (ICDAR 2015)
13th International Conference on Document Analysis and Recognition (ICDAR 2015), Aug 2015, Nancy, France. pp.5
13th International Conference on Document Analysis and Recognition (ICDAR 2015)
13th International Conference on Document Analysis and Recognition (ICDAR 2015), Aug 2015, Nancy, France. pp.5
International audience; —This paper proposes an entity recognition approach in scanned documents referring to their description in database records. First, using the database record values, the corresponding document fields are labeled. Second, ent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::89ade905c321d1aa20a3501755bcad2a
https://doi.org/10.1109/icdar.2015.7333772
https://doi.org/10.1109/icdar.2015.7333772
Autor:
Nihel Kooli, Abdel Belaïd
Publikováno v:
ICPRAM (1)
International Conference on Pattern Recognition Applications and Methods (ICPRAM-2015)
International Conference on Pattern Recognition Applications and Methods (ICPRAM-2015), Jan 2015, Lisbon, Portugal. ⟨10.5220/0005177301650172⟩
International Conference on Pattern Recognition Applications and Methods (ICPRAM-2015)
International Conference on Pattern Recognition Applications and Methods (ICPRAM-2015), Jan 2015, Lisbon, Portugal. ⟨10.5220/0005177301650172⟩
This paper presents an entity recognition approach on documents recognized by OCR (Optical Character Recognition). The recognition is formulated as a task of matching entities in a database with their representations in a document. A pre-processing s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9febaff22db46719740db00492519f51
https://doi.org/10.5220/0005177301650172
https://doi.org/10.5220/0005177301650172