Madhyastha, P., Wang, J.K. orcid.org/0000-0003-0048-3893 and Specia, L. (Accepted: 2018) Defoiling Foiled Image Captions. In: North American Chapter of the Association of Computational Linguistics: Human Language Technologies (NAACL-HLT 2018). North American Chapter of the Association of Computational Linguistics: Human Language Technologies (NAACL HLT), 01-06 Jun 2018, New Orleans, Louisiana. Association for Computational Linguistics . (In Press)
Abstract
We address the task of detecting foiled image captions, i.e. identifying whether a caption contains a word that has been deliberately replaced by a semantically similar word, thus rendering it inaccurate with respect to the image being described. Solving this problem should in principle require a fine-grained understanding of images to detect linguistically valid perturbations in captions. In such contexts, encoding sufficiently descriptive image information becomes a key challenge. In this paper, we demonstrate that it is possible to solve this task using simple, interpretable yet powerful representations based on explicit object information. Our models achieve stateof-the-art performance on a standard dataset, with scores exceeding those achieved by humans on the task. We also measure the upperbound performance of our models using gold standard annotations. Our analysis reveals that the simpler model performs well even without image information, suggesting that the dataset contains strong linguistic bias.
Metadata
Authors/Creators: |
|
||||
---|---|---|---|---|---|
Copyright, Publisher and Additional Information: | © NAACL-HLT 2018. | ||||
Dates: |
|
||||
Institution: | The University of Sheffield | ||||
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) | ||||
Funding Information: |
|
||||
Depositing User: | Symplectic Sheffield | ||||
Date Deposited: | 24 Apr 2018 14:28 | ||||
Last Modified: | 24 Apr 2018 14:28 | ||||
Status: | In Press | ||||
Publisher: | Association for Computational Linguistics | ||||
Refereed: | Yes |