@inproceedings{madhyastha-etal-2018-defoiling,
title = "Defoiling Foiled Image Captions",
author = "Madhyastha, Pranava Swaroop and
Wang, Josiah and
Specia, Lucia",
editor = "Walker, Marilyn and
Ji, Heng and
Stent, Amanda",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-2069",
doi = "10.18653/v1/N18-2069",
pages = "433--438",
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 subtle 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 over multilayer perceptron models. Our models achieve state-of-the-art performance on a recently published dataset, with scores exceeding those achieved by humans on the task. We also measure the upper-bound performance of our models using gold standard annotations. Our study and analysis reveals that the simpler model performs well even without image information, suggesting that the dataset contains strong linguistic bias.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="madhyastha-etal-2018-defoiling">
<titleInfo>
<title>Defoiling Foiled Image Captions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pranava</namePart>
<namePart type="given">Swaroop</namePart>
<namePart type="family">Madhyastha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josiah</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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 subtle 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 over multilayer perceptron models. Our models achieve state-of-the-art performance on a recently published dataset, with scores exceeding those achieved by humans on the task. We also measure the upper-bound performance of our models using gold standard annotations. Our study and analysis reveals that the simpler model performs well even without image information, suggesting that the dataset contains strong linguistic bias.</abstract>
<identifier type="citekey">madhyastha-etal-2018-defoiling</identifier>
<identifier type="doi">10.18653/v1/N18-2069</identifier>
<location>
<url>https://aclanthology.org/N18-2069</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>433</start>
<end>438</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Defoiling Foiled Image Captions
%A Madhyastha, Pranava Swaroop
%A Wang, Josiah
%A Specia, Lucia
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F madhyastha-etal-2018-defoiling
%X 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 subtle 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 over multilayer perceptron models. Our models achieve state-of-the-art performance on a recently published dataset, with scores exceeding those achieved by humans on the task. We also measure the upper-bound performance of our models using gold standard annotations. Our study and analysis reveals that the simpler model performs well even without image information, suggesting that the dataset contains strong linguistic bias.
%R 10.18653/v1/N18-2069
%U https://aclanthology.org/N18-2069
%U https://doi.org/10.18653/v1/N18-2069
%P 433-438
Markdown (Informal)
[Defoiling Foiled Image Captions](https://aclanthology.org/N18-2069) (Madhyastha et al., NAACL 2018)
ACL
- Pranava Swaroop Madhyastha, Josiah Wang, and Lucia Specia. 2018. Defoiling Foiled Image Captions. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 433–438, New Orleans, Louisiana. Association for Computational Linguistics.