{"id":988,"date":"2021-12-15T08:02:56","date_gmt":"2021-12-15T07:02:56","guid":{"rendered":"https:\/\/pageperso.lis-lab.fr\/bernard.espinasse\/nouveausite\/?page_id=988"},"modified":"2024-01-08T15:08:42","modified_gmt":"2024-01-08T14:08:42","slug":"these-maha-mallek","status":"publish","type":"page","link":"https:\/\/pageperso.lis-lab.fr\/bernard.espinasse\/index.php\/these-maha-mallek\/","title":{"rendered":"These Maha Mallek"},"content":{"rendered":"

\"\"<\/strong>Maha Mallek<\/strong>, \u00ab Classification de relations d’un document textuel non structur\u00e9 bas\u00e9e sur le contexte \u00bb. Th\u00e8se en cotutelle entre Aix-Marseille Universit\u00e9 et l’Universit\u00e9 de la Manouba (ENSI), soutenue le 22 d\u00e9cembre 2023 \u00e0 Tunis.<\/p>\n

Manuscrit<\/a><\/span><\/p>\n

R\u00e9sum\u00e9<\/strong><\/span><\/p>\n

\n
\n
\n

La majorit\u00e9 des documents produits et \u00e9chang\u00e9s par les m\u00e9dias et les r\u00e9seaux sociaux sont non structur\u00e9s. En raison de la quantit\u00e9 de ces documents non structur\u00e9s sur le Web, leur exploitation repr\u00e9sente une t\u00e2che fastidieuse voire impossible pour l’\u00eatre humain sans l’aide d’algorithmes d\u00e9di\u00e9s et de syst\u00e8mes informatiques sp\u00e9cialis\u00e9s dans la classification de documents ou l’extraction d’informations. Pour \u00eatre efficaces et pertinents, ces syst\u00e8mes doivent comprendre le contenu de ces documents non structur\u00e9s. Le contexte (ou sujet) d’un document est l’une des informations de base essentielles \u00e0 la compr\u00e9hension de son contenu, et plus le contexte d’un document est pr\u00e9cis, plus sa compr\u00e9hension sera pertinente. Cette recherche propose une approche d’identification pr\u00e9cise du contexte qui est \u00e9valu\u00e9e quantitativement et qualitativement sur plusieurs corpus de r\u00e9f\u00e9rence et compar\u00e9e \u00e0 d’autres syst\u00e8mes d’identification du contexte. Les contextes identifi\u00e9s par notre mod\u00e8le sont beaucoup plus pr\u00e9cis que ceux identifi\u00e9s par ces autres syst\u00e8mes.classification de documents ou d’extraction d’information. Pour \u00eatre efficaces et pertinents, ces syst\u00e8mes doivent comprendre le contenu de ces documents non structur\u00e9s. Le contexte (ou sujet) d’un document est l’une des informations de base essentielles \u00e0 la compr\u00e9hension de son contenu, et plus le contexte d’un document est pr\u00e9cis, plus sa compr\u00e9hension sera pertinente. Cet recherche pr\u00e9sente une approche d’identification pr\u00e9cise du contexte qui est \u00e9valu\u00e9e quantitativement et qualitativement sur plusieurs corpus de r\u00e9f\u00e9rence et compar\u00e9e \u00e0 d’autres syst\u00e8mes d’identification du contexte. Les contextes identifi\u00e9s par notre mod\u00e8le sont beaucoup plus pr\u00e9cis que ceux identifi\u00e9s par ces autres syst\u00e8mes.<\/span><\/p>\n

Abstract<\/em><\/span><\/strong><\/p>\n

The majority of documents produced and exchanged by the media and social networks are unstructured. Due to the amount of unstructured documents on the web, exploiting them is a tedious, if not impossible, task for human beings without the help of dedicated algorithms and computer systems specialised in document classification or information extraction. To be efficient and relevant, these systems need to understand the content of these unstructured documents. The context (or subject) of a document is one of the basic pieces of information essential to understanding its content, and the more precise the context of a document, the more relevant its understanding will be. This research proposes an approach to accurate context identification that is quantitatively and qualitatively evaluated on several reference corpora and compared to other context identification systems. The contexts identified by our model are much more accurate than those identified by these other document classification or information retrieval systems. To be effective and relevant, these systems must understand the content of these unstructured documents. The context (or subject) of a document is one of the basic pieces of information essential to understanding its content, and the more precise the context of a document, the more relevant its understanding will be. This research presents an approach to accurate context identification that is quantitatively and qualitatively evaluated on several reference corpora and compared to other context identification systems. The contexts identified by our model are much more accurate than those identified by these other systems.<\/em><\/span><\/p>\n

 <\/p>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

Maha Mallek, \u00ab Classification de relations d’un document textuel non structur\u00e9 bas\u00e9e sur le contexte \u00bb. Th\u00e8se en cotutelle entre Aix-Marseille Universit\u00e9 et l’Universit\u00e9 de la Manouba (ENSI), soutenue le 22 d\u00e9cembre 2023 \u00e0 Tunis. Manuscrit R\u00e9sum\u00e9 La majorit\u00e9 des documents produits et \u00e9chang\u00e9s par les m\u00e9dias et les r\u00e9seaux sociaux sont non structur\u00e9s. En … <\/p>\n

Continuer la lecture \u00ab\u00a0These Maha Mallek\u00a0\u00bb<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_crdt_document":"","footnotes":""},"class_list":["post-988","page","type-page","status-publish","hentry","entry"],"_links":{"self":[{"href":"https:\/\/pageperso.lis-lab.fr\/bernard.espinasse\/index.php\/wp-json\/wp\/v2\/pages\/988","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/pageperso.lis-lab.fr\/bernard.espinasse\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/pageperso.lis-lab.fr\/bernard.espinasse\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/pageperso.lis-lab.fr\/bernard.espinasse\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/pageperso.lis-lab.fr\/bernard.espinasse\/index.php\/wp-json\/wp\/v2\/comments?post=988"}],"version-history":[{"count":9,"href":"https:\/\/pageperso.lis-lab.fr\/bernard.espinasse\/index.php\/wp-json\/wp\/v2\/pages\/988\/revisions"}],"predecessor-version":[{"id":1707,"href":"https:\/\/pageperso.lis-lab.fr\/bernard.espinasse\/index.php\/wp-json\/wp\/v2\/pages\/988\/revisions\/1707"}],"wp:attachment":[{"href":"https:\/\/pageperso.lis-lab.fr\/bernard.espinasse\/index.php\/wp-json\/wp\/v2\/media?parent=988"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}