Visually grounded meaning representations
Mostra el registre complet Registre parcial de l'ítem
- dc.contributor.author Silberer, Carina
- dc.contributor.author Ferrari, Vittorio
- dc.contributor.author Lapata, Mirella
- dc.date.accessioned 2019-06-26T13:55:13Z
- dc.date.available 2019-06-26T13:55:13Z
- dc.date.issued 2017
- dc.description.abstract In this paper we address the problem of grounding distributional representations of lexical meaning. We introduce a new model which uses stacked autoencoders to learn higher-level representations from textual and visual input. The visual modality is encoded via vectors of attributes obtained automatically from images. We create a new large-scale taxonomy of 600 visual attributes representing more than 500 concepts and 700K images. We use this dataset to train attribute classifiers and integrate their predictions with text-based distributional models of word meaning. We evaluate our model on its ability to simulate word similarity judgments and concept categorization. On both tasks, our model yields a better fit to behavioral data compared to baselines and related models which either rely on a single modality or do not make use of attribute-based input.en
- dc.format.mimetype application/pdf
- dc.identifier.citation Silberer C, Ferrari V, Lapata M. Visually Grounded meaning representations. IEEE Trans Pattern Anal Mach Intell. 2017; 39(11): 2284-97. DOI: 10.1109/TPAMI.2016.2635138
- dc.identifier.doi http://dx.doi.org/10.1109/TPAMI.2016.2635138
- dc.identifier.issn 0162-8828
- dc.identifier.uri http://hdl.handle.net/10230/41865
- dc.language.iso eng
- dc.publisher Institute of Electrical and Electronics Engineers (IEEE)
- dc.relation.ispartof IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017; 39(11): 2284-97.
- dc.rights © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/10.1109/TPAMI.2016.2635138
- dc.rights.accessRights info:eu-repo/semantics/openAccess
- dc.subject.keyword Cognitive simulationen
- dc.subject.keyword Computer visionen
- dc.subject.keyword Distributed representationsen
- dc.subject.keyword Concept learningen
- dc.subject.keyword Connectionism and neural netsen
- dc.subject.keyword Naturallanguage processingen
- dc.title Visually grounded meaning representationsen
- dc.type info:eu-repo/semantics/article
- dc.type.version info:eu-repo/semantics/acceptedVersion