Zobrazeno 1 - 10
of 84
pro vyhledávání: '"Albert Gatt"'
Autor:
Ettore Mariotti, Anna Arias-Duart, Michele Cafagna, Albert Gatt, Dario Garcia-Gasulla, Jose Maria Alonso-Moral
Publikováno v:
IEEE Access, Vol 12, Pp 138870-138880 (2024)
Among the existing eXplainable AI (XAI) approaches, Feature Attribution methods are a popular option due to their interpretable nature. However, each method leads to a different solution, thus introducing uncertainty regarding their reliability and c
Externí odkaz:
https://doaj.org/article/aadbcea98bcb4e1fa724053c74360556
Publikováno v:
Frontiers in Artificial Intelligence, Vol 6 (2023)
When applied to Image-to-text models, explainability methods have two challenges. First, they often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated sequence. This makes explanations expens
Externí odkaz:
https://doaj.org/article/2d11fcb56ab2484abcf36052257019f9
Publikováno v:
Frontiers in Artificial Intelligence, Vol 6 (2023)
Situational context is crucial for linguistic reference to visible objects, since the same description can refer unambiguously to an object in one context but be ambiguous or misleading in others. This also applies to Referring Expression Generation
Externí odkaz:
https://doaj.org/article/47c4b597799c45edb2ed5c2903bf71c2
Publikováno v:
Financial Innovation, Vol 8, Iss 1, Pp 1-20 (2022)
Abstract Twitter sentiment has been shown to be useful in predicting whether Bitcoin’s price will increase or decrease. Yet the state-of-the-art is limited to predicting the price direction and not the magnitude of increase/decrease. In this paper,
Externí odkaz:
https://doaj.org/article/2b77bdce41984b6ea05e43a3b4150e84
Publikováno v:
International Journal of Computational Intelligence Systems, Vol 12, Iss 2 (2019)
We describe an applied methodology to build fuzzy models of geographical expressions, which are meant to be used for natural language generation purposes. Our approach encompasses a language grounding task within the development of an actual data-to-
Externí odkaz:
https://doaj.org/article/a27592307c314944933cdd830e25f983
Autor:
Agata, Savary, Cherifa Ben Khelil, Carlos, Ramisch, Voula, Giouli, Verginica Barbu Mititelu, Najet Hadj Mohamed, Cvetana, Krstev, Chaya, Liebeskind, Hongzhi, Xu, Sara, Stymne, Tunga, Güngör, Thomas, Pickard, Bruno, Guillaume, Eduard, Bejček, Archna, Bhatia, Marie, Candito, Polona, Gantar, Uxoa, Iñurrieta, Albert, Gatt, Jolanta, Kovalevskaite, Timm, Lichte, Nikola, Ljubešić, Monti, Johanna, Carla Parra Escartín, Mehrnoush, Shamsfard, Ivelina, Stoyanova, Veronika, Vincze, Abigail, Walsh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______3684::4a6b68a3252f2673e7b5abbea37d5f4a
https://hdl.handle.net/11574/216660
https://hdl.handle.net/11574/216660
Image captioning models tend to describe images in an object-centric way, emphasising visible objects. But image descriptions can also abstract away from objects and describe the type of scene depicted. In this paper, we explore the potential of a st
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3abe94704c3e750a67ec2e2a6bb5daf2
http://arxiv.org/abs/2211.04971
http://arxiv.org/abs/2211.04971
Publikováno v:
SSRN Electronic Journal.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::027278cefa65a6c546c2428e7f520174
https://doi.org/10.2139/ssrn.4288260
https://doi.org/10.2139/ssrn.4288260
Publikováno v:
Psychological Review, 126(3), 345-373. American Psychological Association
In psycholinguistics, there has been relatively little work investigating conceptualization-how speakers decide which concepts to express. This contrasts with work in natural language generation (NLG), a subfield of artificial intelligence, where muc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c0c5b120f7876b75db864cd4994ee17
https://doi.org/10.1037/rev0000138
https://doi.org/10.1037/rev0000138
Autor:
Lorenzo De Mattei, Michele Cafagna, Huiyuan Lai, Felice Dell'Orletta, Malvina Nissim, Albert Gatt
Publikováno v:
University of Groningen
Proceedings of the 1st Workshop on Evaluating NLG Evaluation (EvalNLGEval'20)
Proceedings of the 1st Workshop on Evaluating NLG Evaluation (EvalNLGEval'20)
An ongoing debate in the NLG community concerns the best way to evaluate systems, with human evaluation often being considered the most reliable method, compared to corpus-based metrics. However, tasks involving subtle textual differences, such as st
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d3e65bc0fb66780ce09da3f84f9aea01
http://arxiv.org/abs/2101.01634
http://arxiv.org/abs/2101.01634