Research
Research Interests
Natural Language Processing, Machine Learning and Information Retrieval
Specific topics:
Neural Language Models
Semantic Information Retrieval
Geographic Information Retrieval (GIR)
Toponym Disambiguation
Word Sense Disambiguation
Ontology learning and population (Mining relationships from text)
Automatic detection of Irony/Humour in text
Sentiment Analysis and Opinion Mining
PhD Students:
Ehab Hassan (2013 - 2017) co-director with Aldo Gangemi - "Reconnaissance d'expériences vécues dans les avis d'utilisateurs : une méthode basée sur les événements.", LIPN
Simon David Hernandez Pérez (2016 - 2019) co-director with Thierry Charnois - "Topic detection and similarity in scientific literature", LIPN
Fernando Lovera (2019 - ) co-director with Thierry Charnois and Yudith Cardinale (Venezuela USB) - "Tweet analysis in the context of natural disasters"
Nabil Moncef Boukhatem (2020 - ) co-director with Leo Liberti (Ecole Polytechnique), CIFRE thesis - "Technical QA"
Hadi Abdine (2020 - ) co-director with Michalis Vazirgiannis (Ecole Polytechnique) - "LLMs and semantics"
Vijini Liyanage (2021 - ) co-director with Adeline Nazarenko, LIPN - "Detection of LLM - generated texts in Academic publications"
Hugo Attali (2023 - ) co-director with Nathalie Pernelle, LIPN - "Graph-based KG analysis and correction"
Mohamed Douib (2023 - ) co-director with Sonia Vanier, LIX (chaire Intelligence Artificielle de Confiance et Responsable X-Crédit Agricole)
Jérémie Dentan (2023 - ) co-director with Sonia Vanier, LIX (chaire Intelligence Artificielle de Confiance et Responsable X-Crédit Agricole)
Bachelor Theses
Merlin Beaufils (2022) "Representational Learning On Websites Using NLP Methodology" co-supervision with Clemens Rosenbaum from ASAPP.inc (USA)
Reviewing and Scientific Responsibilities :
I've been invited to participate as a reviewer for some journals and as a member of program committees for different conferences and workshops.
Most significant ones:
International Conferences and workshops: ESWC 2017-2022; SIGIR 2016, 2017 (short program); ADBIS 2013; IBERAMIA 2014; SOFSEM 16-20; ISWC 2016-2022; EKAW 2016; IJCAI-ECAI 2018-2019, CoNLL 2019, 2020, AAAI 2021, NLDB 2022
National Conferences: CERI (2013-2015); CLiC-IT 2017, 2018; IC 2018, 2019; APIA 2022
Workshops: RISE (2013- ); SAVE-SD (2016- ); KEGeoD @ SAC’2018; RECITAL 2017; SciK 2022; Text2KG; DeepOntoNLP
Journals: The Computer Journal, Data & Knowledge Engineering, Computer Speech and Language, International Journal of Geographical Information Science, Knowledge and Information Systems, Transactions on Information Systems, Information Processing and Management, Springer Nature Computer Science
Member of the mentor board for the student mentorship program at ECIR 2016
Member of the Steering Committee for SemEval-2020 and SemEval-2021
Member of the Scientific Committee of the Labex EFL
Member of the jury for the best PhD thesis prize (prix de la meilleure thèse) ATALA 2019
Member of the Steering Committee for Human Language Technologies of the AFIA (French Association for Artificial Intelligence)
Guest evaluator for the Frontier Science 2019 Call (Conacyt, Mexico)
Senior Area Chair for NAACL 2022 (Sentiment Analysis and Stylistic Analysis)
Area Chair for COLING 2022 (Sentiment and Opinion Mining track)
Scientific Dissemination:
Organization of the 1st International Workshop on the Extraction and Modelling of Knowledge from Scientific Texts (Emc-Sci), satellite workshop of IC 2017, Caen, France
Organization of the Fourth International Workshop at ESWC on Sentic Computing, Sentiment Analysis, Opinion mining and Emotion Detection, satellite workshop at ESWC 2018, Crete, Greece, June 3rd 2018
Organization of task 7: Semantic Relation Extraction and Classification in Scientific Papers at SemEval 2018, co-located with NAACL-HLT 2018, New Orleans, USA
Chair of the ESWC 2018 challenges track (together with D. Reforgiato)
Organization of the 2nd Workshop VADOR (Valorisation des données de la recherche), CORIA-TALN-RJC 2018
Organization of the 2nd Workshop on Deep Learning and Knowledge Graphs (DL4KG), ESWC 2019
Organization of the 3rd Workshop on Deep Learning and Knowledge Graphs (DL4KG), ESWC 2020
Organization of the 4th Workshop on Deep Learning and Knowledge Graphs (DL4KG), ISWC 2021
Organization of the 5th Workshop on Deep Learning and Knowledge Graphs (DL4KG), ISWC 2022
Organization of the 6th Workshop on Deep Learning and Knowledge Graphs (DL4KG), ISWC 2023
Active Research Projects:
Projet d'établissement (BQR) "Plongements lexicaux pour l’acquisition et la structuration de connaissances" (Porteur)
PhilHumans EU Project H2020-MSCA-ITN-2018: local coordinator for the LIPN
Currently member of the RCLN lab involved in the LabEX EFL
Previous Research Projects:
CampusFrance "Polonium" project on sentiment analysis and irony detection (international project with Pedagogical University of Kraków, Poland)
Golfred:G Machine reading for narrative generation of spatial experiences in service robots
“Cartographie de la diaspora des savoirs par fouille sémantique des résultats recherche sur le web” (projet ECOS-NORD in cooperation with UNAM, Mexico)
MOANO - Models and Tools for pervasive applications focusing on Territory Discovery http://moano.liuppa.univ-pau.fr/
Extraction automatique de bases de connaissances lexicalisées à partir de textes (LIFO, Université d'Orléans)
TEXT-MESS 2.0 (subproject UPV: TEXT-ENTERPRISE 2.0: Text comprehension techniques applied to the needs of the Enterprise 2.0)
TEXT-MESS: Minería de Textos Inteligente, Interactiva y Multilingüe basada en Tecnología del Lenguaje Humano (subproject UPV: MiDEs)
Sistema de Búsqueda de Respuestas Inteligente basado en Agentes (AraEsp)
ICT for EU-India Cross-Cultural Dissemination
R2D2: Recuperación de Respuestas en Documentos Digitalizados
Formulación y Evaluación de Modelos para Resolver Preguntas a partir de Textos en Español empleando Información Lingüística
CIAO SENSO: Combining Corpus-Based and Knowledge-Based Methods for Word Sense Disambiguation
Thesis:
Ph.D "cum laude", Universidad Politécnica de Valencia, dissertation: "Toponym Disambiguation in Information Retrieval". 29th October 2010. European doctor mention. Panel: Paul Clough, Ross Purves, Emilio Sanchis, Mark Sanderson, Diana Santos https://riunet.upv.es/handle/10251/8912
Invited Talks:
Mining Scholarly Publications for Scientific Knowledge Graph Construction, Workshop on Deep Learning meets Ontologies and Natural Language Processing, FOIS 2020, Bolzano (virtual), 16 September 2020
Towards the Automatic Generation of States of the art: current trends and challenges in the analysis of scientific texts, 7th LKE Symposium, Dublin 28-31 October 2019
Improving access to scientific literature: a semantic IR perspective, Conferencia Española de Recuperación de la Información (CERI 2018), Zaragoza, 27 June 2018
Information Géographique, textes et média sociaux, Atelier extraction de connaissances en données spatialisés (EXCES), SAGEO 2017, Rouen, 6 November 2017 (slides)
Computational Semantics for Next-generation Natural Language Processing applications, 2a Escuela de otoño de tecnologías del lenguaje, Cholula, Mexico, 27-28 September 2016
Análisis Semántico, LKE2015 Symposium, BUAP, Mexico, 27 October 2015 (Keynote Speaker)
NLP and Geographical Information Systems, 3th Workshop on Semantic Web and New Technologies, Benemérita Universidad Autónoma de Puebla, Mexico, 12 July 2010 (Keynote Speaker)
Awards and Grants:
DR78 grant from "Regione Liguria" for the completion of B.Sc. thesis in a foreign research center, 2002
FPI grant from "Generalitat Valenciana" (GVA) for the Ph.D. program at Universidad Politécnica de Valencia, 2006-2010
GVA grant for a 3-months doctoral stage at FBK-IRST, Trento, under the supervision of Bernardo Magnini, 2009
Visiting professor grant from the University of Cagliari, may 2017
Best poster award at the 5th Franco-Polish forum for Research and Innovation
CV:
A short CV in English (last update: September 2022)
this page is under construction.