Persona
di Buono Maria Pia

di Buono Maria Pia

Ricercatori/trici a t. d. ex art.24 c.3
DIPARTIMENTO STUDI LETTERARI, LINGUISTICI E COMPARATI
Course Catalogue:
https://unior.coursecatalogue.cineca.it/docente-ma...

Agenda

Cv Allegato

Curriculum Vitae

Maria Pia di Buono ha conseguito il dottorato di ricerca in Scienze della Comunicazione con una tesi in Linguistica Computazionale presso l’Università degli Studi di Salerno.
Ha lavorato come post-doc presso l’Università di Zagabria - Facoltà di Ingegneria Elettrica e Informatica e presso centri di eccellenza europei, come il Center for Cognitive Interaction Technology - Semantic Computing group dell’Università di Bielefeld (Germania), prendendo parte a progetti nazionali e internazionali.
Dal 2019 è ricercatrice di Didattica delle Lingue Moderne (L-LIN/02) presso l’Università degli Studi di Napoli “L’Orientale” dove insegna Traduttologia Generale e Tecnologie del linguaggio.
È stata componente del primo collegio del Dottorato Nazionale in Intelligenza Artificiale - Area AI & Society - XXXVII ciclo.
In collaborazione con alcuni colleghi, nel 2021 ha vinto il premio EuropeanaTech Challenge for Europeana Artificial Intelligence/Machine Learning Datasets e nel 2022 il terzo posto nella Challenge 4 dell’EU DATATHON, organizzato dal Publications Office dell’Unione Europea.
Nel 2024, insieme a due soci, ha fondato Dahlia s.r.l., il primo spin-off dell'Università di Napoli "L'Orientale", che propone soluzioni di natural language processing e intelligenza artificiale.
Le sue ricerche riguardano il trattamento automatico del linguaggio e la traduzione automatica, con particolare attenzione ai temi della rappresentazione semantica, della creazione di risorse linguistiche e della valutazione dei modelli del linguaggio. Numerose sono le sue pubblicazioni, spesso realizzate insieme ad autori internazionali.

Pubblicazioni (81)

Dataset (8)

Premi e riconoscimenti (3)

Best Poster Award, conferito da The Fourth Conference on Language Data Knowledge 2023 - 2023
EU Datathon - 2022 edition, conferito da Publications of office of the European Union - 2022
Challenge for Europeana AI/ML Datasets, conferito da Europeana - 2021
No Results Found

Partecipazioni scientifiche (2)

Socio effettivo o corrispondente - I-LanD Centro di Ricerca Interuniversitario (Italia) (2020 - )
No Results Found

Comitati editoriali

Guest Editor di rivista o collana editoriale - RASSEGNA ITALIANA DI LINGUISTICA APPLICATA - ISSN: 0033-9725 - Rome Italy: Bulzoni Editore Srl (2021 - 2021)
No Results Found

Ricerca e didattica presso enti (4)

Incarico svolto presso: Università degli Studi di NAPOLI "L'Orientale" - Ricercatore universitario a t.d. (02/08/2022 - 01/08/2024)
Incarico svolto presso: Università degli Studi di NAPOLI "L'Orientale" - Ricercatore universitario a t.d. (02/08/2019 - 01/08/2022)
Post-doc researcher presso: University of Bielefeld - Ricercatore all estero (01/03/2019 - 31/07/2019)
Post-doc researcher presso: University of Zagreb - Ricercatore all estero (01/10/2016 - 14/01/2019)
No Results Found

Congressi (8)

Program chair (presidente/responsabile del comitato scientifico) - KESA 2018 - The International Workshop on Knowledge Extraction and Semantic Annotation (22/04/2024 - 26/04/2024)
Program committee (membro del comitato scientifico) - Workshop on Multi-word Units in Machine Translation and Translation Technology (MUMTTT 2022) (01/01/2022 - )
Program chair (presidente/responsabile del comitato scientifico) - KESA 2017 - The International Workshop on Knowledge Extraction and Semantic Annotation (23/04/2017 - 27/04/2017)
Program chair (presidente/responsabile del comitato scientifico) - KESA 2016 - The International Workshop on Knowledge Extraction and Semantic Annotation (21/02/2016 - 25/02/2016)
Program chair (presidente/responsabile del comitato scientifico) - KESA 2015 - The International Workshop on Knowledge Extraction and Semantic Annotation (19/04/2015 - 24/04/2015)
Partecipazione al comitato organizzativo - NooJ 2014 International Conference (02/06/2014 - 05/06/2014)
No Results Found

Network di ricerca (7)

COST ACTION - CA22126 - European Network On Lexical Innovation (ENEOLI) - Neology is the study of lexical innovation in natural languages, in multiple contexts and over time. Lexical innovation is a massive, permanent and universal phenomenon. From a strictly linguistic point of view, the study of neology “contributes to a better understanding of the lexical system of a given language and its evolution” (Sablayrolles 2019: 7), while from an extralinguistic point of view, “the inventory of neologisms also gives much information about language communities in their material lives and social representations” (ibid.). The key challenges addressed by the network may be summarised thus: 1) Define the core terminology of neology conceived as a discipline through the creation of a born-digital specialised multilingual glossary (none exist currently) in order to facilitate research on an international scale; 2) Adapt digital methodologies and tools to identify and account for lexical innovation; thanks to the involvement of institutions, experts and the general public (crowdsourcing), increase the awareness of lexical creations and their societal implications, foster creativity in mother tongues, clarity in institutional communication and in science; 3) Carry out comparative studies on lexical innovation in European languages, with a particular focus on borrowings and their equivalents; 4) Provide specific training in neology for translators, editors, journalists, technical writers and teachers through a specific protocol that could be replicated for any European language. Conferences, training schools and short-term scientific missions are also planned in order to achieve the aforementioned goals. (06/10/2023 - 05/10/2027)
COST ACTION - CA21167, Universality, diversity and idiosyncracy in language technology - The CA21167 COST Action, UniDive, is an interdisciplinary scientific network devoted to universality, diversity and idiosyncrasy in language technology. It main objective is to reconcile language diversity with rapid progress in language technology. It embraces both inter- and intra-language diversity, i.e. a diversity understood both in terms of the differences among the existing languages and of the variety of linguistic phenomena exhibited within a language. It gathers about 250 interdisciplinary experts (linguists, computational linguists, computer scientists, psycholinguists, and industrials) from almost 40 COST countries (36 of which are COST countries). It represents dozens of languages from many different language genera. (23/09/2022 - 22/09/2026) (23/09/2022 - 22/09/2026)
COST ACTION - CA18209 - European network for Web-centred linguistic data science (NexusLinguarum) - The main aim of this Action is to promote synergies across Europe between linguists, computer scientists, terminologists, and other stakeholders in industry and society, in order to investigate and extend the area of linguistic data science. We understand linguistic data science as a subfield of the emerging “data science”, which focuses on the systematic analysis and study of the structure and properties of data at a large scale, along with methods and techniques to extract new knowledge and insights from it. Linguistic data science is a specific case, which is concerned with providing a formal basis to the analysis, representation, integration and exploitation of language data (syntax, morphology, lexicon, etc.). In fact, the specificities of linguistic data are an aspect largely unexplored so far in a big data context. (28/10/2019 - 27/04/2024)
COST ACTION - CA18231 - Multi3Generation: Multi-task, Multilingual, Multi-modal Language Generation (Multi3Generation) Downloads - Language generation (LG) is a crucial technology if machines are to communicate with humans seamlessly using human natural language. A great number of different tasks within Natural Language Processing (NLP) are language generation tasks, and being able to effectively perform these tasks implies (1) that machines are equipped with world knowledge that can require multi-modal processing and reasoning (e.g. textual, visual and auditory inputs, or sensory data streams), and (2) the study of strong, novel Machine Learning (ML) methods (e.g. structured prediction, generative models), since virtually all state-of-the-art NLP models are learned from data. Moreover, human languages can differ wildly in their surface realisation (i.e. scripts) as well as their internal structure (i.e. grammar), which suggests that multilinguality is a central goal if machines are to perform seamless language generation. Language generation technologies would greatly benefit both public and private services offered to EU citizens in a multilingual Europe, and have strong economic and societal impacts. (09/09/2019 - 08/03/2024)
Ontology-Lexica Community Group - The mission of the Ontology-Lexicon community group is to: (1) Develop models for the representation of lexica (and machine readable dictionaries) relative to ontologies. These lexicon models are intended to represent lexical entries containing information about how ontology elements (classes, properties, individuals etc.) are realized in multiple languages. In addition, the lexical entries contain appropriate linguistic (syntactic, morphological, semantic and pragmatic) information that constrains the usage of the entry. (2) Demonstrate the added value of representing lexica on the Semantic Web, in particularly focusing on how the use of linked data principles can allow for the re-use of existing linguistic information from resource such as WordNet. (3) Provide best practices for the use of linguistic data categories in combination with lexica. (4) Demonstrate that the creation of such lexica in combination with the semantics contained in ontologies can improve the performance of NLP tools. (5) Bring together people working on standards for representing linguistic information (syntactic, morphological, semantic and pragmatic) building on existing initiatives, and identifying collaboration tracks for the future. (6) Cater for interoperability among existing models to represent and structure linguistic information. (7) Demonstrate the added value of applications relying on the use of the combination of lexica and ontologies. (21/07/2014 - )
COST ACTION - IS1312 - Structuring Discourse in Multilingual Europe (TextLink) - ffective discourse in any language is characterized by clear relations between sentences and coherent structure. But languages vary in how relations and structure are signalled. While monolingual dictionaries and grammars can characterise the words and sentences of a language and bilingual dictionaries can do the same between languages, there is nothing similar for discourse. For discourse, however, discourse-annotated corpora are becoming available in individual languages. The Action will facilitate European multilingualism by (1) identifying and creating a portal into such resources within Europe – including annotation tools, search tools, and discourse-annotated corpora; (2) delineating the dimensions and properties of discourse annotation across corpora; (3) organising these properties into a sharable taxonomy; (4) encouraging the use of this taxonomy in subsequent discourse annotation and in cross-lingual search and studies of devices that relate and structure discourse; and (5) promoting use of the portal, its resources and sharable taxonomy. With partners from across Europe, TextLink will unify numerous but scattered linguistic resources on discourse structure. With its resources searchable by form and/or meaning and a source of valuable correspondences, TextLink will enhance the experience and performance of human translators, lexicographers, language technology and language learners alike. (11/04/2014 - 10/04/2018)
COST ACTION - IC1207 - Parsing and multi-word expressions. Towards linguistic precision and computational efficiency in natural language processing (PARSEME) - This Action aims at increasing and enhancing the support of the European multilingual heritage from Information and Communication Technologies (ICT). This general aim is addressed through improving linguistic representativeness, precision and computational efficiency of Natural Language Processing (NLP) applications. The Action focuses on the major bottleneck of these applications: Multi-Word Expressions (MWEs), i.e. sequences of words with unpredictable properties such as “to count somebody in” or “to take a haircut”. A breakthrough in their modelling and processing can only result from a coordinated effort of multidisciplinary experts in different languages. COST is the most adequate framework answering this need. Fourteen European languages will be addressed from a cross-theoretical and cross-methodological perspective, necessary for coping with current fragmentation issues. Expected deliverables include enhanced language resources and tools, as well as recommendations of best practices for cutting-edge MWE-aware language models. The Action will lead to a better understanding of the nature of MWEs. It will establish a long-lasting collaboration within a multilingual network of MWE specialists. It will pave the way towards competitive next generation text processing tools which will pay greater attention to language phenomena. (08/03/2013 - 30/04/2017)
No Results Found

Tutoraggio

tutorship - Altro - GIORDANO LUCA
No Results Found

Supervisione di dottorandi o post-doc esterni

Dottorando - Cosimo Palma - Università di PISA - (01/11/2021 - )

Insegnamenti offerta formativa corrente (3)

No Results Found

Ricevimento

Video

Risorse Utili