14 results on '"Aseervatham, Sujeevan"'
Search Results
2. Semi-structured document categorization with a semantic kernel
- Author
-
Aseervatham, Sujeevan, primary and Bennani, Younès, additional
- Published
- 2009
- Full Text
- View/download PDF
3. A CONCEPT VECTOR SPACE MODEL FOR SEMANTIC KERNELS
- Author
-
ASEERVATHAM, SUJEEVAN, primary
- Published
- 2009
- Full Text
- View/download PDF
4. A local Latent Semantic Analysis-based kernel for document similarities
- Author
-
Aseervatham, Sujeevan, primary
- Published
- 2008
- Full Text
- View/download PDF
5. A Semantic Kernel for Semi-structured DocumentS
- Author
-
Aseervatham, Sujeevan, primary, Viennet, Emmanuel, additional, and Bennani, Younès, additional
- Published
- 2007
- Full Text
- View/download PDF
6. bitSPADE: A Lattice-based Sequential Pattern Mining Algorithm Using Bitmap Representation
- Author
-
Aseervatham, Sujeevan, primary, Osmani, Aomar, additional, and Viennet, Emmanuel, additional
- Published
- 2006
- Full Text
- View/download PDF
7. Semi-structured document categorization with a semantic kernel
- Author
-
Younès Bennani, Sujeevan Aseervatham, Aseervatham, Sujeevan, Laboratoire d'Informatique de Paris-Nord (LIPN), and Université Paris 13 (UP13)-Institut Galilée-Université Sorbonne Paris Cité (USPC)-Centre National de la Recherche Scientifique (CNRS)
- Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI] ,Support Vector Machine ,Text Categorization ,Computer science ,Semantic analysis (machine learning) ,[INFO.INFO-TT] Computer Science [cs]/Document and Text Processing ,02 engineering and technology ,computer.software_genre ,Semantic Similarity ,[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] ,03 medical and health sciences ,Naive Bayes classifier ,Structured document ,[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] ,Semantic similarity ,Artificial Intelligence ,0202 electrical engineering, electronic engineering, information engineering ,030304 developmental biology ,0303 health sciences ,business.industry ,Unified Medical Language System ,Semi-Structured Data ,[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG] ,Similitude ,[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing ,Support vector machine ,Kernel method ,Categorization ,Ranking ,Kernel (statistics) ,Signal Processing ,Mercer Kernel ,ComputingMethodologies_DOCUMENTANDTEXTPROCESSING ,020201 artificial intelligence & image processing ,Computer Vision and Pattern Recognition ,Artificial intelligence ,Tree kernel ,business ,computer ,Software ,Natural language processing - Abstract
Since a decade, text categorization has become an active field of research in the machine learning community. Most of the approaches are based on the term occurrence frequency. The performance of such surface-based methods can decrease when the texts are too complex, i.e., ambiguous. One alternative is to use the semantic-based approaches to process textual documents according to their meaning. Furthermore, research in text categorization has mainly focused on ''flat texts'' whereas many documents are now semi-structured and especially under the XML format. In this paper, we propose a semantic kernel for semi-structured biomedical documents. The semantic meanings of words are extracted using the unified medical language system (UMLS) framework. The kernel, with a SVM classifier, has been applied to a text categorization task on a medical corpus of free text documents. The results have shown that the semantic kernel outperforms the linear kernel and the naive Bayes classifier. Moreover, this kernel was ranked in the top 10 of the best algorithms among 44 classification methods at the 2007 Computational Medicine Center (CMC) Medical NLP International Challenge.
- Published
- 2009
8. Méthodes à noyaux appliquées aux textes structurés
- Author
-
Sujeevan Aseervatham, Emmanuel Viennet, Laboratoire d'Informatique de Paris-Nord (LIPN), Université Sorbonne Paris Cité (USPC)-Institut Galilée-Université Paris 13 (UP13)-Centre National de la Recherche Scientifique (CNRS), and Aseervatham, Sujeevan
- Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI] ,[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing ,Kernel ,Support Vector Machine ,[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] ,[INFO.INFO-TT] Computer Science [cs]/Document and Text Processing ,[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG] ,Natural Language Processing ,[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] - Abstract
National audience; De nombreuses techniques d'apprentissage numérique appliquées au traitement de données textuelles utilisent une représentation du texte en "sac de mot". Ce codage, qui a l'avantage de la simplicité, n'utilise que les fréquences d'apparition des mots dans les documents et perd toute information liée à l'ordre des éléments (ordre des mots, structure en paragraphes ou sections, etc). Depuis une petite dizaine d'années, une nouvelle famille d'algorithme d'apprentissage, basée sur la notion de noyaux, fait l'objet d'intenses recherches. Ces noyaux permettent de définir des mesures de similarité utilisables dans de nombreux algorithmes d'apprentissage statistique (de l'analyse discriminante de Fisher aux machines à vecteur de support). Récemment, l'utilisation de noyaux spécifiques pour le traitement de données textuelles structurées a commencé à faire l'objet de recherches. Dans le cadre de la sous-tâche 3.12 du projet InfoM@gic, le LIPN a décidé de travailler sur l'application de ces méthodes à noyau au traitement de données textuelles structurées. Ce rapport intermédiaire présente un bref état de l'art dans ce domaine. Nous passons en revue les principaux types de noyaux proposés ces dernières années pour le traitement des séquences et plus généralement des données structurées (arbres, graphes).
- Published
- 2008
9. A Concept Vector Space Model for Semantic Kernels
- Author
-
Sujeevan Aseervatham, Laboratoire d'Informatique de Paris-Nord (LIPN), Université Paris 13 (UP13)-Institut Galilée-Université Sorbonne Paris Cité (USPC)-Centre National de la Recherche Scientifique (CNRS), and Aseervatham, Sujeevan
- Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI] ,Support Vector Machine ,Computer science ,[INFO.INFO-TT] Computer Science [cs]/Document and Text Processing ,02 engineering and technology ,computer.software_genre ,Semantic Similarity ,[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] ,[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] ,Artificial Intelligence ,Polynomial kernel ,String kernel ,020204 information systems ,0202 electrical engineering, electronic engineering, information engineering ,Probabilistic latent semantic analysis ,business.industry ,Pattern recognition ,[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG] ,[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing ,Kernel ,Kernel method ,Kernel embedding of distributions ,Kernel (statistics) ,Radial basis function kernel ,020201 artificial intelligence & image processing ,Artificial intelligence ,Text categorization ,Tree kernel ,business ,computer ,Natural language processing - Abstract
International audience; Kernels are widely used in Natural Language Processing as similarity measures within inner-product based learning methods like the Support Vector Machine. The Vector Space Model (VSM) is extensively used for the spatial representation of the documents. However, it is purely a statistical representation. In this paper, we present a Concept Vector Space Model (CVSM) representation which uses linguistic prior knowledge to capture the meanings of the documents. We also propose a linear kernel and a latent kernel for this space. The linear kernel takes advantage of the linguistic concepts whereas the latent kernel combines statistical and linguistic concepts. Indeed, the latter kernel uses latent concepts extracted by the Latent Semantic Analysis (LSA) in the CVSM. The kernels were evaluated on a text categorization task in the biomedical domain. The Ohsumed corpus, well known for being difficult to categorize, was used. The results have shown that the CVSM improves performance compared to the VSM.
- Published
- 2008
10. bitSPADE: A Lattice-Based Sequential Pattern Mining Algorithm Using Bitmap Representation
- Author
-
Aomar Osmani, Emmanuel Viennet, Sujeevan Aseervatham, Aseervatham, Sujeevan, Laboratoire d'Informatique de Paris-Nord (LIPN), and Université Paris 13 (UP13)-Institut Galilée-Université Sorbonne Paris Cité (USPC)-Centre National de la Recherche Scientifique (CNRS)
- Subjects
Association rule learning ,Computer science ,02 engineering and technology ,computer.file_format ,[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG] ,computer.software_genre ,[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] ,020204 information systems ,Lattice (order) ,0202 electrical engineering, electronic engineering, information engineering ,Bitmap ,Data Mining ,020201 artificial intelligence & image processing ,Frequent Sequential Patterns ,Data mining ,Sequential Pattern Mining ,computer ,Algorithm ,Sequence Mining - Abstract
Sequential pattern mining allows to discover temporal relationship between items within a database. The patterns can then be used to generate association rules. When the databases are very large, the execution speed and the memory usage of the mining algorithm become critical parameters. Previous research has focused on either one of the two parameters. In this paper, we present bitSPADE, a novel algorithm that combines the best features of SPAM, one of the fastest algorithm, and SPADE, one of the most memory efficient algorithm. Moreover, we introduce a new pruning strategy that enables bitSPADE to reach high performances. Experimental evaluations showed that bitSPADE ensures an efficient tradeoff between speed and memory usage by outperforming SPADE by both speed and memory usage factors more than 3.4 and SPAM by a memory consumption factor up to more than an order of magnitude.
- Published
- 2006
11. A Semantic Kernel for Semi-Structured Documents
- Author
-
Sujeevan Aseervatham, Younès Bennani, Emmanuel Viennet, Laboratoire d'Informatique de Paris-Nord (LIPN), Université Paris 13 (UP13)-Institut Galilée-Université Sorbonne Paris Cité (USPC)-Centre National de la Recherche Scientifique (CNRS), and Aseervatham, Sujeevan
- Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI] ,Computer science ,[INFO.INFO-TT] Computer Science [cs]/Document and Text Processing ,02 engineering and technology ,computer.software_genre ,Semantic network ,[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] ,Semantic Similarities ,Naive Bayes classifier ,Kernel (linear algebra) ,Text mining ,[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] ,Semantic computing ,Support Vector Machines ,0202 electrical engineering, electronic engineering, information engineering ,[INFO.INFO-BI] Computer Science [cs]/Bioinformatics [q-bio.QM] ,business.industry ,05 social sciences ,[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG] ,Support vector machine ,[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing ,Kernel ,Kernel method ,Ranking ,Kernel (statistics) ,[INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR] ,020201 artificial intelligence & image processing ,[INFO.INFO-IR] Computer Science [cs]/Information Retrieval [cs.IR] ,Artificial intelligence ,Text categorization ,0509 other social sciences ,Tree kernel ,[INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM] ,050904 information & library sciences ,business ,computer ,Natural language processing - Abstract
International audience; Natural Language Processing has emerged as an active field of research in the machine learning community. Several methods based on statistical information have been proposed. However, with the linguistic complexity of the texts, semantic-based approaches have been investigated. In this paper, we propose a Semantic Kernel for semi-structured biomedical documents. The semantic meanings of words are extracted using the UMLS framework. The kernel, with a SVM classifier, has been applied to a text categorization task on a medical corpus of free text documents. The results have shown that the Semantic Kernel outperforms the Linear Kernel and the Naive Bayes classifier. Moreover, this kernel was ranked in the top ten of the best algorithms among 44 classification methods at the 2007 CMC Medical NLP International Challenge.
12. Mining short sequential patterns for hepatitis type detection
- Author
-
Sujeevan Aseervatham, Aomar OSMANI, Aseervatham, Sujeevan, P. Berka and B. Crémilleux, Laboratoire d'Informatique de Paris-Nord (LIPN), and Université Paris 13 (UP13)-Institut Galilée-Université Sorbonne Paris Cité (USPC)-Centre National de la Recherche Scientifique (CNRS)
- Subjects
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] ,viruses ,[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG] ,Sequence Mining - Abstract
International audience; This paper presents the framework we have developed to classify patients according to the type of hepatitis. To detect the type of virus, once the data have been prepared and encoded in a suitable way, we have extracted the sequential patterns for each virus. Tempo- ral dierences between hepatitis B and C can then be seen as patterns that are frequent in one data series and infrequent in the other. The B virus and C virus patterns, extracted under specic constraints, were used to classify patients according to the hepatitis virus. In this work, we especially studied the use of very short patterns for virus type detec- tion. However, the framework allows the mining and the use of longer patterns.The results have shown that in more than half of cases, short patterns can reveal the type of virus with a low level of errors.
13. Apprentissage à base de Noyaux Sémantiques pour le Traitement de Données Textuelles
- Author
-
Sujeevan Aseervatham, Laboratoire d'Informatique de Paris-Nord (LIPN), Université Paris 13 (UP13)-Institut Galilée-Université Sorbonne Paris Cité (USPC)-Centre National de la Recherche Scientifique (CNRS), Université Paris-Nord - Paris XIII, Younès Bennani(Younes.Bennani@lipn.univ-paris13.fr), and Aseervatham, Sujeevan
- Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI] ,Support Vector Machine ,[INFO.INFO-TT] Computer Science [cs]/Document and Text Processing ,[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG] ,[INFO] Computer Science [cs] ,données ,Apprentissage ,[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] ,traitement ,[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing ,Machine Learning ,Noyaux ,Séparateurs à Vaste Marge ,[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] ,Kernels ,informatique ,Semantic Similarity Measures ,sémantique ,[INFO]Computer Science [cs] ,base ,Text categorization ,thèse ,Catégorisation de texte ,textuelles ,Mesure de Similarité Sémantique - Abstract
Since the early eighties, statistical methods and, more specifically, the machine learning for textual data processing have known a considerable growth of interest. This is mainly due to the fact that the number of documents to process is growing exponentially. Thus, expert-based methods have become too costly, losing the research focus to the profit of machine learning-based methods.In this thesis, we focus on two main issues. The first one is the processing of semi-structured textual data with kernel-based methods. We present, in this context, a semantic kernel for documents structured by sections under the XML format. This kernel captures the semantic information with the use of an external source of knowledge e.g., a thesaurus. Our kernel was evaluated on a medical document corpus with the UMLS thesaurus. It was ranked in the top ten of the best methods, according to the F1-score, among 44 algorithms at the 2007 CMC Medical NLP International Challenge. The second issue is the study of the use of latent concepts extracted by statistical methods such as the Latent Semantic Analysis (LSA). We present, in a first part, kernels based on linguistic concepts from external sources and on latent concepts of the LSA. We show that a kernel integrating both kinds of concepts improves the text categorization performances. Then, in a second part, we present a kernel that uses local LSAs to extract latent concepts. Local latent concepts are used to have a more finer representation of the documents., Depuis le début des années 80, les méthodes statistiques et, plus spécifiquement, les méthodes d'apprentissage appliquées au traitement de données textuelles connaissent un intérêt grandissant. Cette tendance est principalement due au fait que la taille des corpus est en perpétuelle croissance. Ainsi, les méthodes utilisant le travail d'experts sont devenues des processus coûteux perdant peu à peu de leur popularité au profit des systèmes d'apprentissage.Dans le cadre de cette thèse, nous nous intéressons principalement à deux axes.Le premier axe porte sur l'étude des problématiques liées au traitement de données textuelles structurées par des approches à base de noyaux. Nous présentons, dans ce contexte, un noyau sémantique pour les documents structurés en sections notamment sous le format XML. Le noyau tire ses informations sémantiques à partir d'une source de connaissances externe, à savoir un thésaurus. Notre noyau a été testé sur un corpus de documents médicaux avec le thésaurus médical UMLS. Il a été classé, lors d'un challenge international de catégorisation de documents médicaux, parmi les 10 méthodes les plus performantes sur 44. Le second axe porte sur l'étude des concepts latents extraits par des méthodes statistiques telles que l'analyse sémantique latente (LSA). Nous présentons, dans une première partie, des noyaux exploitant des concepts linguistiques provenant d'une source externe et des concepts statistiques issus de la LSA. Nous montrons qu'un noyau intégrant les deux types de concepts permet d'améliorer les performances. Puis, dans un deuxième temps, nous présentons un noyau utilisant des LSA locaux afin d'extraire des concepts latents permettant d'obtenir une représentation plus fine des documents.
14. Méthodes à noyaux appliquées aux textes structurés: Rapport d'avancement 1
- Author
-
Sujeevan Aseervatham, Emmanuel Viennet, Laboratoire d'Informatique de Paris-Nord (LIPN), Université Paris 13 (UP13)-Institut Galilée-Université Sorbonne Paris Cité (USPC)-Centre National de la Recherche Scientifique (CNRS), InfoMagic (Cap Digital), and Aseervatham, Sujeevan
- Subjects
données structurées ,Méthodes à noyaux ,tal ,[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] ,[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG] ,texte - Abstract
De nombreuses techniques d'apprentissage numérique appliquées au traitement de données textuelles utilisent une représentation du texte en "sac de mot". Ce codage, qui a l'avantage de la simplicité, n'utilise que les fréquences d'apparition des mots dans les documents et perd toute information liée à l'ordre des éléments (ordre des mots, structure en paragraphes ou sections, etc). Depuis une petite dizaine d'années, une nouvelle famille d'algorithme d'apprentissage, basée sur la notion de noyaux, fait l'objet d'intenses recherches. Ces noyaux permettent de définir des mesures de similarité utilisables dans de nombreux algorithmes d'apprentissage statistique (de l'analyse discriminante de Fisher aux machines à vecteur de support). Récemment, l'utilisation de noyaux spécifiques pour le traitement de données textuelles structurées a commencé à faire l'objet de recherches. Dans le cadre de la sous-tâche 3.12 du projet InfoM@gic, le LIPN a décidé de travailler sur l'application de ces méthodes à noyau au traitement de données textuelles structurées. Ce rapport intermédiaire présente un bref état de l'art dans ce domaine. Nous passons en revue les principaux types de noyaux proposés ces dernières années pour le traitement des séquences et plus généralement des données structurées (arbres, graphes).
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.