CINECA IRIS Institutional Research Information System
IRIS è l'Anagrafe della ricerca dell'Università degli Studi di Trento, e ha lo scopo di raccogliere, documentare, conservare e diffondere, anche ad accesso aperto, la produzione scientifica degli autori afferenti all'Università degli Studi di Trento.
EnglishIn this paper, we aim to understand whether current language and vision (LaVi) models truly grasp the interaction between the two modalities. To this end, we propose an extension of the MS-COCO dataset, FOIL-COCO, which associates images with both correct and ‘foil’ captions, that is, descriptions of the image that are highly similar to the original ones, but contain one single mistake (‘foil word’). We show that current LaVi models fall into the traps of this data and perform badly on three tasks: a) caption classification (correct vs. foil); b) foil word detection; c) foil word correction. Humans, in contrast, have near-perfect performance on those tasks. We demonstrate that merely utilising language cues is not enough to model FOIL-COCO and that it challenges the state-of-the-art by requiring a fine-grained understanding of the relation between text and image.
FOIL it! Find One mismatch between Image and Language caption / Shekhar, Ravi; Pezzelle, Sandro; Klimovich, Yauhen; Herbelot, Aurelie; Nabi, Moin; Sangineto, Enver; Bernardi, Raffaella. - ELETTRONICO. - (2017), pp. 255-265. ((Intervento presentato al convegno ACL tenutosi a Vancouver nel July 30th - August 4th, 2017 [10.18653/v1/P17-1024 ].
| Titolo: | FOIL it! Find One mismatch between Image and Language caption. | |
| Autori: | Shekhar, Ravi; Pezzelle, Sandro; Klimovich, Yauhen; Herbelot, Aurelie; Nabi, Moin; Sangineto, Enver; Bernardi, Raffaella | |
| Autori Unitn: | ||
| Titolo del volume contenente il saggio: | ACL 2017 The 55th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 1 (Long Papers) | |
| Luogo di edizione: | Stroudsburg PA | |
| Casa editrice: | Association for Computational Linguistics | |
| Anno di pubblicazione: | 2017 | |
| Codice identificativo Scopus: | 2-s2.0-85040908564 | |
| Codice identificativo WOS: | WOS:000493984800024 | |
| ISBN: | 978-194562675-3 | |
| Handle: | http://hdl.handle.net/11572/175244 | |
| Citazione: | FOIL it! Find One mismatch between Image and Language caption / Shekhar, Ravi; Pezzelle, Sandro; Klimovich, Yauhen; Herbelot, Aurelie; Nabi, Moin; Sangineto, Enver; Bernardi, Raffaella. - ELETTRONICO. - (2017), pp. 255-265. ((Intervento presentato al convegno ACL tenutosi a Vancouver nel July 30th - August 4th, 2017 [10.18653/v1/P17-1024 ]. | |
| Appare nelle tipologie: | 04.1 Saggio in atti di convegno (Paper in Proceedings) |
File in questo prodotto:
| File | Descrizione | Tipologia | Licenza | |
|---|---|---|---|---|
| foil_acl17.pdf | Versione editoriale (Publisher’s layout) | Tutti i diritti riservati (All rights reserved) | Open Access Visualizza/Apri |
http://hdl.handle.net/11572/175244
Copyright © 2022