Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Tiziano Fagni"'
Publikováno v:
PLoS ONE, Vol 16, Iss 5, p e0251415 (2021)
The recent advances in language modeling significantly improved the generative capabilities of deep neural models: in 2019 OpenAI released GPT-2, a pre-trained language model that can autonomously generate coherent, non-trivial and human-like text sa
Externí odkaz:
https://doaj.org/article/f931b7470e03463eb28a4bce3caa5e05
Publikováno v:
WebSci 2022-14th ACM Web Science Conference, pp. 154–163, Barcelona, Spain, 26-29/06/2022
The recent advances in natural language generation provide an additional tool to manipulate public opinion on social media. Even though there has not been any report of malicious exploit of the newest generative techniques so far, disturbing human-li
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c2abcef8e8bea88af7490e200a8890c5
https://openportal.isti.cnr.it/doc?id=people______::c81e9c91b0dd0807f5ff2c9df2d8f042
https://openportal.isti.cnr.it/doc?id=people______::c81e9c91b0dd0807f5ff2c9df2d8f042
Autor:
Tiziano Fagni, Stefano Cresci
Predicting the political leaning of social media users is an increasingly popular task, given its usefulness for electoral forecasts, opinion dynamics models and for studying the political dimension of polarization and disinformation. Here, we propos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b1e9d31044a58ad38bb33405425480e6
Publikováno v:
Information retrieval (Boston) 21 (2018): 208–229. doi:10.1007/s10791-017-9318-6
info:cnr-pdr/source/autori:Carrara F.; Esuli A.; Fagni T.; Falchi F.; Moreo Fernandez A./titolo:Picture it in your mind: generating high level visual representations from textual descriptions/doi:10.1007%2Fs10791-017-9318-6/rivista:Information retrieval (Boston)/anno:2018/pagina_da:208/pagina_a:229/intervallo_pagine:208–229/volume:21
info:cnr-pdr/source/autori:Carrara F.; Esuli A.; Fagni T.; Falchi F.; Moreo Fernandez A./titolo:Picture it in your mind: generating high level visual representations from textual descriptions/doi:10.1007%2Fs10791-017-9318-6/rivista:Information retrieval (Boston)/anno:2018/pagina_da:208/pagina_a:229/intervallo_pagine:208–229/volume:21
In this paper we tackle the problem of image search when the query is a short textual description of the image the user is looking for. We choose to implement the actual search process as a similarity search in a visual feature space, by learning to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a8b4aef4b851fc5859eb22c142153aa3
http://www.cnr.it/prodotto/i/384745
http://www.cnr.it/prodotto/i/384745
Publikováno v:
Information systems frontiers (Dordrecht. Online) 20 (2018): 993–1011. doi:10.1007/s10796-018-9833-z
info:cnr-pdr/source/autori:Avvenuti M.; Cresci S.; Del Vigna F.; Fagni T.; Tesconi M./titolo:CrisMap: a Big Data Crisis Mapping System Based on Damage Detection and Geoparsing/doi:10.1007%2Fs10796-018-9833-z/rivista:Information systems frontiers (Dordrecht. Online)/anno:2018/pagina_da:993/pagina_a:1011/intervallo_pagine:993–1011/volume:20
info:cnr-pdr/source/autori:Avvenuti M.; Cresci S.; Del Vigna F.; Fagni T.; Tesconi M./titolo:CrisMap: a Big Data Crisis Mapping System Based on Damage Detection and Geoparsing/doi:10.1007%2Fs10796-018-9833-z/rivista:Information systems frontiers (Dordrecht. Online)/anno:2018/pagina_da:993/pagina_a:1011/intervallo_pagine:993–1011/volume:20
Natural disasters, as well as human-made disasters, can have a deep impact on wide geographic areas, and emergency responders can benefit from the early estimation of emergency consequences. This work presents CrisMap, a Big Data crisis mapping syste
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::59c57878813640c55c9f5afdf693d816
http://hdl.handle.net/11568/907520
http://hdl.handle.net/11568/907520
Autor:
Tiziano Fagni, Fabrizio Sebastiani
Publikováno v:
Journal of the American Society for Information Science and Technology
61 (2010): 2256–2265. doi:10.1002/asi.21411
info:cnr-pdr/source/autori:Fagni T.; Sebastiani F./titolo:Selecting negative examples for hierarchical text classification: an experimental comparison/doi:10.1002%2Fasi.21411/rivista:Journal of the American Society for Information Science and Technology (Print)/anno:2010/pagina_da:2256/pagina_a:2265/intervallo_pagine:2256–2265/volume:61
61 (2010): 2256–2265. doi:10.1002/asi.21411
info:cnr-pdr/source/autori:Fagni T.; Sebastiani F./titolo:Selecting negative examples for hierarchical text classification: an experimental comparison/doi:10.1002%2Fasi.21411/rivista:Journal of the American Society for Information Science and Technology (Print)/anno:2010/pagina_da:2256/pagina_a:2265/intervallo_pagine:2256–2265/volume:61
Hierarchical text classification (HTC) approaches have recently attracted a lot of interest on the part of researchers in human language technology and machine learning, since they have been shown to bring about equal, if not better, classification a
Publikováno v:
Information retrieval (Boston) 11 (2008): 287–313. doi:10.1007/s10791-008-9047-y
info:cnr-pdr/source/autori:Esuli A.; Fagni T.; Sebastiani F./titolo:Boosting multi-label hierarchical text categorization/doi:10.1007%2Fs10791-008-9047-y/rivista:Information retrieval (Boston)/anno:2008/pagina_da:287/pagina_a:313/intervallo_pagine:287–313/volume:11
info:cnr-pdr/source/autori:Esuli A.; Fagni T.; Sebastiani F./titolo:Boosting multi-label hierarchical text categorization/doi:10.1007%2Fs10791-008-9047-y/rivista:Information retrieval (Boston)/anno:2008/pagina_da:287/pagina_a:313/intervallo_pagine:287–313/volume:11
Hierarchical Text Categorization (HTC) is the task of generating (usually by means of supervised learning algorithms) text classifiers that operate on hierarchically structured classification schemes. Notwithstanding the fact that most large-sized cl
Publikováno v:
30th Annual ACM Symposium on Applied Computing, pp. 1053–1059, Salamanca, ES, 13-17/04/2015
info:cnr-pdr/source/autori:Berardi G.; Esuli A.; Fagni T.; Sebastiani F./congresso_nome:30th Annual ACM Symposium on Applied Computing/congresso_luogo:Salamanca, ES/congresso_data:13-17%2F04%2F2015/anno:2015/pagina_da:1053/pagina_a:1059/intervallo_pagine:1053–1059
SAC
info:cnr-pdr/source/autori:Berardi G.; Esuli A.; Fagni T.; Sebastiani F./congresso_nome:30th Annual ACM Symposium on Applied Computing/congresso_luogo:Salamanca, ES/congresso_data:13-17%2F04%2F2015/anno:2015/pagina_da:1053/pagina_a:1059/intervallo_pagine:1053–1059
SAC
Classifying companies by industry sector is an important task in finance, since it allows investors and research analysts to analyse specific subsectors of local and global markets for investment monitoring and planning purposes. Traditionally this c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aac0fdf951518deaedd699e99f6fa3c1
http://dl.acm.org/citation.cfm?id=2695722&CFID=734381158&CFTOKEN=34893976
http://dl.acm.org/citation.cfm?id=2695722&CFID=734381158&CFTOKEN=34893976
Publikováno v:
30th Annual ACM Symposium on Applied Computing, pp. 585–588, Salamanca, ES, 13-17/04/2015
info:cnr-pdr/source/autori:Berardi G.; Esuli A.; Fagni T.; Sebastiani F./congresso_nome:30th Annual ACM Symposium on Applied Computing/congresso_luogo:Salamanca, ES/congresso_data:13-17%2F04%2F2015/anno:2015/pagina_da:585/pagina_a:588/intervallo_pagine:585–588
SAC
info:cnr-pdr/source/autori:Berardi G.; Esuli A.; Fagni T.; Sebastiani F./congresso_nome:30th Annual ACM Symposium on Applied Computing/congresso_luogo:Salamanca, ES/congresso_data:13-17%2F04%2F2015/anno:2015/pagina_da:585/pagina_a:588/intervallo_pagine:585–588
SAC
The mass adoption of smartphone and tablet devices has boosted the growth of the mobile applications market. Confronted with a huge number of choices, users may encounter difficulties in locating the applications that meet their needs. Sorting applic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e20cf6a6f94161159433acb408350a6b
http://www.cnr.it/prodotto/i/344465
http://www.cnr.it/prodotto/i/344465
Publikováno v:
Pattern recognition and image analysis 20 (2010): 21–28. doi:10.1134/S1054661810010025
info:cnr-pdr/source/autori:Fagni T.; Falchi F.; Sebastiani F./titolo:Image classification via adaptive ensembles of descriptor-specific classifiers/doi:10.1134%2FS1054661810010025/rivista:Pattern recognition and image analysis/anno:2010/pagina_da:21/pagina_a:28/intervallo_pagine:21–28/volume:20
info:cnr-pdr/source/autori:Fagni T.; Falchi F.; Sebastiani F./titolo:Image classification via adaptive ensembles of descriptor-specific classifiers/doi:10.1134%2FS1054661810010025/rivista:Pattern recognition and image analysis/anno:2010/pagina_da:21/pagina_a:28/intervallo_pagine:21–28/volume:20
An automated classification system usually consists of (i) a supervised learning algorithm for automatically generating classifiers from training data, and (ii) a representation scheme for converting the training objects into vectorial representation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::80f76d6b9aee0711054135e22c6ade52
https://openportal.isti.cnr.it/doc?id=people______::620d7bd788adee3552c7af02aeac083e
https://openportal.isti.cnr.it/doc?id=people______::620d7bd788adee3552c7af02aeac083e