Michele Cafagna
Michele Cafagna
Phd Candidate - Marie Curie, Institute of Linguistics and Language Technology, University of Malta
Verified email at
Cited by
Cited by
VALSE: A task-independent benchmark for vision and language models centered on linguistic phenomena
L Parcalabescu, M Cafagna, L Muradjan, A Frank, I Calixto, A Gatt
arXiv preprint arXiv:2112.07566, 2021
Geppetto carves italian into a language model
L De Mattei, M Cafagna, F Dell'Orletta, M Nissim, M Guerini
arXiv preprint arXiv:2004.14253, 2020
Norm It!: Lexical Normalization for Italian and Its Downstream Effects for Dependency Parsing
R Van Der Goot, A Ramponi, T Caselli, M Cafagna, L De Mattei
Proceedings of the 12th International Conference on Language Resources and …, 2020
What Vision-Language ModelsSee'when they See Scenes
M Cafagna, K van Deemter, A Gatt
arXiv preprint arXiv:2109.07301, 2021
Invisible to people but not to machines: Evaluation of style-aware HeadlineGeneration in absence of reliable human judgment
L De Mattei, M Cafagna, F Dell’Orletta, M Nissim
Proceedings of the Twelfth Language Resources and Evaluation Conference …, 2020
Change-it@ evalita 2020: Change headlines, adapt news, generate
L De Mattei, M Cafagana, F Dell’Orletta, M Nissim, A Gatt
Evaluation Campaign of Natural Language Processing and Speech Tools for Italian, 2020
Embeddings Shifts as Proxies for Different Word Use in Italian Newspapers.
M Cafagna, L De Mattei, M Nissim
CLiC-it, 2019
HL dataset: visually-grounded description of scenes, actions and rationales
M Cafagna, K van Deemter, A Gatt
arXiv preprint arXiv:2302.12189, 2023
On the interaction of automatic evaluation and task framing in headline style transfer
L De Mattei, M Cafagna, H Lai, F Dell'Orletta, M Nissim, A Gatt
arXiv preprint arXiv:2101.01634, 2021
Interpreting vision and language generative models with semantic visual priors
M Cafagna, LM Rojas-Barahona, K van Deemter, A Gatt
Frontiers in Artificial Intelligence 6, 1220476, 2023
Suitable Doesn't Mean Attractive. Human-Based Evaluation of Automatically Generated Headlines.
M Cafagna, L De Mattei, D Bacciu, M Nissim
CLiC-it, 2019
ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
I Kesen, A Pedrotti, M Dogan, M Cafagna, EC Acikgoz, L Parcalabescu, ...
arXiv preprint arXiv:2311.07022, 2023
HL Dataset: Grounding High-Level Linguistic Concepts in Vision
M Cafagna, K van Deemter, A Gatt
Proceedings of the 16th International Natural Language Generation Conference …, 2023
Understanding cross-modal interactions in V&L models that generate scene descriptions
M Cafagna, K van Deemter, A Gatt
arXiv preprint arXiv:2211.04971, 2022
Embeddings-based detection of word use variation in italian newspapers
M Cafagna, L De Mattei, M Nissim
IJCoL. Italian Journal of Computational Linguistics 6 (6-2), 9-22, 2020
TextFocus: Assessing the Faithfulness of Feature Attribution Methods Explanations in Natural Language Processing
E Mariotti, A Arias-Duart, M Cafagna, A Gatt, D Garcia-Gasulla, ...
IEEE Access, 2024
Training procedure and system for artificial intelligence intended for the analysis of mammographic data for the identification or exclusion of the presence of breast cancer
C Aliprandi, M Cafagna, L De Mattei, A Tesei
US Patent App. 17/582,180, 2022
Headline Generation and Analysis of Writing Styles in Journalism
Emerging Topics at the Fourth Italian Conference on Computational Linguistics
R Basili, S Montemagni
IJCoL. Italian Journal of Computational Linguistics 4 (4-1), 7-10, 2018
The system can't perform the operation now. Try again later.
Articles 1–19