A5023816166- Natural Language Processing Techniques
- Semantic Web and Ontologies
- Topic Modeling
- linguistics and terminology studies
- Digital Humanities and Scholarship
- Lexicography and Language Studies
- Library Science and Information Systems
- Data Mining Algorithms and Applications
- Speech and dialogue systems
- Rough Sets and Fuzzy Logic
- Bayesian Modeling and Causal Inference
- Advanced Database Systems and Queries
- Service-Oriented Architecture and Web Services
- Advanced Text Analysis Techniques
- Classical Antiquity Studies
- Mathematics, Computing, and Information Processing
- Data Management and Algorithms
- Web Data Mining and Analysis
- Historical and Linguistic Studies
- Linguistics and language evolution
- Business Process Modeling and Analysis
- Constraint Satisfaction and Optimization
- Data Visualization and Analytics
- Authorship Attribution and Profiling
- Particle Accelerators and Free-Electron Lasers
Institute for Computational Linguistics “A. Zampolli”
2014-2023
Consorzio Roma Ricerche
2023
Deutsches Elektronen-Synchrotron DESY
2022
National Research Council
2018-2021
National Academies of Sciences, Engineering, and Medicine
2016-2020
Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo"
2016
University of Florence
2012
Ospedale di Livorno
2011
University of Pisa
2008-2010
IMT School for Advanced Studies Lucca
2008-2010
The paper presents an approach for adding probabilistic reasoning to ontologies. We show how extended form of Bayesian network can be extracted from existing ontology. structure the Network is obtained by means analysis classes and their relationships, initial distributions are considering instances. resulting offers capabilities that satisfy interesting set queries.
Abstract The adoption of Semantic Web technologies in the lexicographic field, has been driven by need to ensure construction lexical resources that are interoperable and can be shared reused scientific communities. In this context, OntoLex W3C working group proposed OntoLex-Lemon model aimed at providing rich linguistic grounding for ontologies. It includes representation morphological syntactic properties entries as well their meaning with respect an ontology or vocabulary. This article...
This article illustrates the progresses made in representing a multilingual and multi-alphabetical Old Occitan medico-botanical lexicon context of project Dictionnaire de Termes Médico-botaniques l’Ancien (DiTMAO). The chosen lexical model reference is lemon, which has been extended accordingly to some specific linguistic features lexicon. In particular, issues solutions about modeling multiword phenomena are discussed, as way they managed through LexO, web editor developed project.
Despite the presence of many systems for developing and managing structured taxonomies and/or SKOS models a given domain which small documents set are accessible, production maintenance these knowledge bases is still very expensive time consuming process. This paper proposes solution assisting expert users in development management base, including ontologies modeling structures relationships. The proposed accelerates by crawling exploiting different kinds sources (in multiple languages with...
With this paper we describe an ontology-driven system that performs relation extraction over textual data. The exploits expert knowledge of the domain, including lexical resources, in form ontology to drive patterns using manually annotated texts. Such are then applied order identify candidates for extraction. Paired with basic, reliable named-entity-level text annotation, results discovery relations among entities Italian newspaper articles. In paper, and measure its performance.
Traduco is a web-based collaborative tool aimed at supporting the translation of texts that pose particular challenging interpretative issues. Nowadays, Computer-Assisted Translation (CAT) tools are mainly applied to technical manuals or legislative and speeding up process. extends most standard components traditional CAT with specific features necessary support interpretation complex (like Babylonian Talmud, we here present as case study), which comprehension goes beyond its printing: it...
In this work we propose a model for the representation of narrative literary text. The is structured in an ontology and lexicon constituting knowledge base that can be queried by system. This ontology, as well describing actors, locations, situations found text, provides explicit formal timeline story. We will focus on specific case study, selected portion Homer's Odyssey, particular required to answer selection salient queries, formulated scholar. being carried out within framework Semantic...
Abstract Different solutions are offered today for modelling multilingual terminological data. In this article, we focus on the description of two approaches: one hand, model proposed in context ISO TC 37/SC 3, based adoption Terminological Markup Framework/TermBase eXchange standards; other ‘Lemon’ and, more generally, Ontology Web Language adopted framework Semantic Web. The aim study is to propose a contrastive multilevel analysis between these paradigms, with ultimate goal highlighting...
In this paper we present a digital process for the explicitation of textual, linguistic and semantic content historical manuscripts. The proposed workflow is composed sequence incremental steps, each which described both on methodological practical perspective. steps are: 1) visualization structuring metadata, 2) transcription, 3) structural encoding, 4) annotation, 5) lexical conceptual structuring.
This article discusses a possible approach combining existing technologies for Natural Language Processing (NLP), Knowledge Representation and Reasoning (KRR) Data Visualization in coherent Decision Support System (DSS) aimed to formulate verify specific interpretative hypotheses about certain text. The chosen developing this system implies (i.) the customization integration of tools automatic text annotation (first all, linguistic, lexicographic semantic) (ii.) construction user-friendly...
Abstract The purpose of this research is to build an ontology the masters appearing in Babylonian Talmud (BT). built so far has been shared as a Linked Open Data and it will be linked existing vocabularies. This work developed context Translation Project, where more than eighty Talmudists are working together, since 2012, at translation (comprehensive explicative notes glossaries) into Italian. construction resource involved application tools leveraging on computational linguistics...