The research groups and laboratories of the Cnr-Istituto di Linguistica Computazionale “Antonio Zampolli” are incubators of new ideas and technological solutions based on the integration and sharing of skills, infrastructures and technologies.
Research aimed at the development of computational models of language behaviour to study the connection between grammatical competence, use of language and neurophysiological and psycho-cognitive correlates of verbal communication.
Head of the Laboratory: Vito Pirrelli
Design and development of models, methods, algorithms and technologies for Natural Language Processing, with a focus on the Italian language: multi-level linguistic annotation of texts, extraction of domain-specific information from document collections, design and development of application prototypes, etc.
Optimisation of research in the field of Language Engineering and the production cycle of language resources through the adoption of standards, the exchange of good practices for interoperability, recycling and reuse of available results in terms of data and tools; definition of models for the creation, representation, extension and maintenance of computational lexicons, terminological and ontological repositories, corpora and language technologies; development of technological solutions for the creation of a distributed and cooperative research infrastructure aimed at establishing new access functionalities, interoperability and sharing of language resources and tools.
Head of the Group: Monica Monachini
KLAB (Knowledge Lexica & Applications Bridging) deals with models, methodologies and tools representation, construction, automatic text extraction, integration and use of lexical, terminological and ontological resources. Knowledge representation is a very vast field, born in the context of Artificial Intelligence (AI), in which the group aims to study and investigate the relationship between language and surrogate representations of the world and specialised domains of knowledge, typically formalised by ontologies. In the analysis of this relationship, computational lexicons and domain terminologies play a crucial role, as essential connecting elements between the orthographic units of the text and the entities (classes, instances, relations) that populate the ontologies. In the field of representation, KLAB investigates the aspects of lexical and knowledge variability (with particular regard to diachrony) not yet sufficiently studied and properly formalised. On the side of Natural Language Processing (NLP), the group experiments with techniques that exploit lexical, terminological and conceptual resources as supporting elements for the traditional stochastic processes.
TEMADH Text Enhancement, Text Mining, Text Analysis for Digital Humanities deals with methods and strategies oriented toward the recovery and enhancement of intangible cultural heritage and the development of software systems for text analysis, text annotation, and semantically relevant information extraction and processing.