Research output per year
Research output per year
Personal profile
About
I work on Natural Language Processing, mainly on Natural Language Generation and the interface between language and vision in neural, multimodal models.
Link to Utrecht University staff page
Fingerprint
Dive into the research topics where Albert Gatt is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Publication network from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
-
A Systematic Analysis of Large Language Models as Soft Reasoners: The Case of Syllogistic Inferences
Bertolazzi, L., Gatt, A. & Bernardi, R., Nov 2024, EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Al-Onaizan, Y., Bansal, M. & Chen, Y.-N. (eds.). Association for Computational Linguistics (ACL), p. 13882-13905 24 p. (EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
Open AccessFile -
Context-aware Visual Storytelling with Visual Prefix Tuning and Contrastive Learning
Song, Y., Paperno, D. & Gatt, A., 2024, p. 384-401.Research output: Contribution to conference › Paper › Academic
Open AccessFile -
How and where does CLIP process negation?
Quantmeyer, V., Mosteiro Romero, P. & Gatt, A., Aug 2024, ALVR 2024. Association for Computational Linguistics, p. 59-72 14 p.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
Open AccessFile -
TextFocus: Assessing the Faithfulness of Feature Attribution Methods Explanations in Natural Language Processing
Mariotti, E., Arias-Duart, A., Cafagna, M., Gatt, A., Garcia-Gasulla, D. & Alonso-Moral, J. M., 31 May 2024, In: IEEE Access. 12, p. 138870-138880 11 p.Research output: Contribution to journal › Article › Academic › peer-review
Open AccessFile -
ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
Kesen, I., Pedrotti, A., Dogan, M., Cafagna, M., Acikgoz, E. C., Parcalabescu, L., Calixto, I., Frank, A., Gatt, A., Erdem, A. & Erdem, E., Jun 2024.Research output: Contribution to conference › Paper › Academic