Cerca
Menu
Foto del docente

Marianna Marcella Bolognesi

Full Professor

Department of Modern Languages, Literatures, and Cultures

Academic discipline: GLOT-01/A Historical and General Linguistics

Collaborations

Collaboration with:
CNR - ISTI
Country:
Italy
Description:
From Cognitive Linguistics to Language Engineering, and Back In the past decade, advancements in deep learning, particularly in the field of natural language processing (NLP) and text mining, have significantly enhanced semantic analysis tasks such as text classification, word sense disambiguation, machine translation, text summarization, question answering, and sentiment analysis. This progress is largely attributed to the concept of word embedding, a word’s meaning representation obtained through numeric coordinates, also known as vectors. Current word embeddings, derived from large textual corpora, have demonstrated efficacy but raise questions about their alignment with human language processing. The WEMB project aims to address this by pursuing two objectives: firstly, gaining a deeper understanding of how word embeddings align with human language processing, and secondly, leveraging this understanding to develop a new generation of embeddings for NLP tasks. The project employs a “from mind to application and back” approach, bridging the expertise of UniBO in language processing with ISTI-CNR’s proficiency in NLP. WEMB focuses on three key aspects: Embeddings and Cross-Modality: Investigating the relationship between embeddings that incorporate cross-modal information (e.g., from text and images) and traditional text-based embeddings in language processing. Embeddings and Misspellings: Exploring the connection between embeddings and misspellings, a prevalent linguistic behavior in a growing number of texts for various reasons. Embeddings and Word Senses: Examining the relationship between embeddings and word senses, particularly among different embeddings associated with different senses of the same ambiguous word. Through these investigations, WEMB aims to contribute to both a theoretical understanding of word embeddings in human language processing and the practical development of enhanced embeddings for NLP applications.
Formal collaboration with:
Università degli Studi di BOLOGNA
Country:
Italy
Description:
Research group ABSTRACTION (ERC-2021-STG-101039777) https://www.abstractionproject.eu/ https://site.unibo.it/abstraction/it The ABSTRACTION project has the goal of understanding the mechanisms of abstractions in the human mind and language. The research group is based at UniBo and involves the PI (Bolognesi), 2 PhDs (Collacciani e Lamarra) and a a pre-doc (Genovese,) and two postdocs (Villani, Rambelli), a developer (Ferrari) and a project manager (Attianese). More information can be found on the project's websites.
Formal collaboration with:
University of Oxford
Country:
United Kingdom
Description:
2017-2019 Research team focused on the study of metaphor, within the research program Creative Multilingualism (https://www.creativeml.ox.ac.uk/research/metaphor). Responsibility: design and carry out experimental studies focused on the functioning of the metaphor in multilingual and multicultural environments, with particular attention to the link between creativity and bilingualism. Organizing and participating in events for academics and the public, where the results of the research are disseminated. Dissemination of scientific results through articles published in international journals and articles for the public. Collaborators: Professor Katrin Kohl Dr Ana Werkman Horvat.
Formal collaboration with:
Metaphor Lab Amsterdam, University of Amsterdam
Country:
Netherlands
Description:
2015-2017 CogVim project (Marie Curie Actions fellowship for Career Development, COGVIM n° 629076 - Project Acronym: COGVIM; Call identifier FP7-PEOPLE-2013-IEF). In these two years, having won a Marie Curie grant, I worked at the University of Amsterdam, coordinating and implementing the CogVim project (Cognitive Grounding of Visual Metaphor: https://cogvim.org/). Responsibility: coordination of the project, implementation of each declared work package, communication with the European Community in relation to the required reports, dissemination of scientific results. Collaborators: Professor Gerard Steen (project supervisor at the host site) Professor Ken MacRae Professor Piek Vossen Professor Diane Pecher Professor Alessandro Lenci Professor Charles Forceville
Formal collaboration with:
Metaphor Lab Amsterdam, Free University of Amsterdam
Country:
Netherlands
Description:
In 2013-2014 I collaborated with Metaphor Lab at the Free University of Amsterdam (VU University) for the construction of a corpus of visual metaphors (VisMet 1.0 project). Role: Coordinator of the project for the construction of the VisMet corpus (http://www.vismet.org/VisMet/) Responsibility: definition of the procedure for the identification of metaphorical images, definition of the protocol for annotation, preparation of the contents and structure of the corpus, including the filters necessary to select the images, design of the website (implemented by a programmer technician), manual annotation of the images on all levels of analysis, coordination of the team responsible for annotations, collection of authorizations for the reproduction of images online. Collaborators: Professor Gerard Steen. Research assistants: Esther van den Berg and Romy van den Heerik

Latest news

View all RSS