Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Boroş, Emanuela"'
Autor:
Boros, Emanuela, Ehrmann, Maud
This paper investigates the presence of OCR-sensitive neurons within the Transformer architecture and their influence on named entity recognition (NER) performance on historical documents. By analysing neuron activation patterns in response to clean
Externí odkaz:
http://arxiv.org/abs/2409.16934
Autor:
González-Gallardo, Carlos-Emiliano, Boros, Emanuela, Girdhar, Nancy, Hamdi, Ahmed, Moreno, Jose G., Doucet, Antoine
Large language models (LLMs) have been leveraged for several years now, obtaining state-of-the-art performance in recognizing entities from modern documents. For the last few months, the conversational agent ChatGPT has "prompted" a lot of interest i
Externí odkaz:
http://arxiv.org/abs/2303.17322
Identifying and exploring emerging trends in the news is becoming more essential than ever with many changes occurring worldwide due to the global health crises. However, most of the recent research has focused mainly on detecting trends in social me
Externí odkaz:
http://arxiv.org/abs/2301.11318
In this paper, we propose a recent and under-researched paradigm for the task of event detection (ED) by casting it as a question-answering (QA) problem with the possibility of multiple answers and the support of entities. The extraction of event tri
Externí odkaz:
http://arxiv.org/abs/2104.06969
Autor:
Boros, Emanuela, Doucet, Antoine
This paper summarizes the participation of the Laboratoire Informatique, Image et Interaction (L3i laboratory) of the University of La Rochelle in the Recognizing Ultra Fine-grained Entities (RUFES) track within the Text Analysis Conference (TAC) ser
Externí odkaz:
http://arxiv.org/abs/2104.06048
Autor:
Boroş, Emanuela
Du point de vue du traitement automatique des langues (TAL), l’extraction des événements dans les textes est la forme la plus complexe des processus d’extraction d’information, qui recouvrent de façon plus générale l’extraction des entit
Externí odkaz:
http://www.theses.fr/2018SACLS302/document
Autor:
Oberbichler, Sarah1 sarah.oberbichler@uibk.ac.at, Boroş, Emanuela2 emanuela.boros@univ-lr.fr, Doucet, Antoine2 antoine.doucet@univ-lr.fr, Marjanen, Jani3 jani.marjanen@helsinki.fi, Pfanzelter, Eva1 eva.pfanzelter@uibk.ac.at, Rautiainen, Juha4 juha.rautiainen@helsinki.fi, Toivonen, Hannu5 hannu.toivonen@helsinki.fi, Tolonen, Mikko3 mikko.tolonen@helsinki.fi
Publikováno v:
Journal of the Association for Information Science & Technology. Feb2022, Vol. 73 Issue 2, p225-239. 15p. 4 Diagrams.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.