Arthur Amalvy
- Laboratoire Informatique d'Avignon (LIA)
Presentation
I am currently a postdoctoral researcher at the Institute of Information Science at Academia Sinica in Taiwan. My current research themes are at the intersection of knowledge graphs and large language models. Specifically, I'm working on improving temporal awareness in large language models, and on their interaction with temporal knowledge bases to improve factuality and knowledge edition. I obtained my PhD at the Laboratoire Informatique d'Avignon under the supervision of Vincent Labatut and Richard Dufour. My PhD is about character networks extraction in literary texts, and how character networks can effectively serve as representation for such texts. Extracting character networks includes a number of natural language processing subtasks I'm interested in: named entity recognition, coreference resolution, alias resolution, quote detection, speaker attribution... This research led to the creation of the Python library Renard, a toolkit to automatically extract character networks. I also participate to the France robotics cup every year with my team! https://sharpattack.fr/en/Online Identities
Education
Teaching
2023-2024
2022-2023
2021-2022
Previous Industry Experience
Softwares
Other
Contact Informations
Publications
Publications
|
|
De l'annotation intégrale à l'analyse des réseaux de personnages : un modèle pour la REN dans les textes littéraires en françaisRevue TAL : traitement automatique des langues, A paraître, 66 (1) |
|
|
Interconnected Kingdoms: Comparing 'A Song of Ice and Fire' Adaptations Across Media Using Complex NetworksSocial Network Analysis and Mining, 2024, 14, pp.199. ⟨10.1007/s13278-024-01365-z⟩ |
|
|
Renard: A Modular Pipeline for Extracting Character Networks from Narrative TextsJournal of Open Source Software, 2024, 9 (98), pp.6574. ⟨10.21105/joss.06574⟩ |
|
|
Du repérage à l'analyse : un modèle pour la reconnaissance d'entités nommées dans les textes littéraires en françaisDigital Humanities 2025, Jul 2025, Lisbonne, Portugal |
|
|
Persistent Homology of Topic Networks for the Prediction of Reader Curiosity63rd Annual Meeting of the Association for Computational Linguistics (ACL), Association for Computational Linguistics, Jul 2025, Vienna, France |
|
|
The Role of Natural Language Processing Tasks in Automatic Literary Character Network Construction31st International Conference on Computational Linguistics (COLING), Jan 2025, Abu Dhabi, United Arab Emirates. pp.8462-8473 |
|
|
Dynamique des relations dans Lorenzaccio : modélisation par réseaux complexesJournées d’Informatique Théâtrale, ICTT, Oct 2024, Avignon, France |
IA : bienfait commun ou piège capitaliste ?3ème édition du festival Pint of science, May 2024, Avignon, France |
|
|
|
Apprendre à classer le contexte pour la reconnaissance d'entités nommées en utilisant un jeu de données synthétiqueCOnférence en Recherche d’Information et Applications (CORIA), Apr 2024, La Rochelle, France |
|
|
The Role of Global and Local Context in Named Entity Recognition61st Annual Meeting of the Association for Computational Linguistics (ACL), Association for Computational Linguistics, Jul 2023, Toronto, Canada. pp.714-722, ⟨10.18653/v1/2023.acl-short.62⟩ |
|
|
Learning to Rank Context for Named Entity Recognition Using a Synthetic DatasetConference on Empirical Methods in Natural Language Processing (EMNLP), ACL, Dec 2023, Singapore, Singapore. pp.10372-10382 |
|
|
BERT meets d'Artagnan: Data Augmentation for Robust Character Detection in NovelsWorkshop on Computational Methods in the Humanities (COMHUM), Jun 2022, Lausanne, Switzerland |
|
|
Remplacement de mentions pour l'adaptation d'un corpus de reconnaissance d'entités nommées à un domaine cible29ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN), Jun 2022, Avignon, France. pp.198-205 |
|
|
Data Augmentation for Robust Character Detection in Fantasy NovelsWorkshop on Computational Methods in the Humanities (ComHum), Jun 2022, Lausanne, Switzerland |
|
|
Traitement du langage et modélisation de relations pour la représentation unifiée de documents narratifsMeetup LIAvignon, Nov 2022, Avignon, France. 2022 |
|
|
Annotation Guidelines for Corpus Novelties: Part 2 - Alias ResolutionLaboratoire Informatique d'Avignon. 2024 |
|
|
Annotation Guidelines for Corpus Novelties: Part 1 – Named Entity RecognitionLaboratoire Informatique d'Avignon. 2024 |
|
|
Traitement du langage naturel appliqué à la représentation de textes narratifs par réseaux de personnageInformatique et langage [cs.CL]. Université d'Avignon, 2024. Français. ⟨NNT : 2024AVIG0116⟩ |