@inproceedings{suhr-etal-2017-corpus,
title = "A Corpus of Natural Language for Visual Reasoning",
author = "Suhr, Alane and
Lewis, Mike and
Yeh, James and
Artzi, Yoav",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-2034",
doi = "10.18653/v1/P17-2034",
pages = "217--223",
abstract = "We present a new visual reasoning language dataset, containing 92,244 pairs of examples of natural statements grounded in synthetic images with 3,962 unique sentences. We describe a method of crowdsourcing linguistically-diverse data, and present an analysis of our data. The data demonstrates a broad set of linguistic phenomena, requiring visual and set-theoretic reasoning. We experiment with various models, and show the data presents a strong challenge for future research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suhr-etal-2017-corpus">
<titleInfo>
<title>A Corpus of Natural Language for Visual Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alane</namePart>
<namePart type="family">Suhr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Yeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Artzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Barzilay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new visual reasoning language dataset, containing 92,244 pairs of examples of natural statements grounded in synthetic images with 3,962 unique sentences. We describe a method of crowdsourcing linguistically-diverse data, and present an analysis of our data. The data demonstrates a broad set of linguistic phenomena, requiring visual and set-theoretic reasoning. We experiment with various models, and show the data presents a strong challenge for future research.</abstract>
<identifier type="citekey">suhr-etal-2017-corpus</identifier>
<identifier type="doi">10.18653/v1/P17-2034</identifier>
<location>
<url>https://aclanthology.org/P17-2034</url>
</location>
<part>
<date>2017-07</date>
<extent unit="page">
<start>217</start>
<end>223</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Corpus of Natural Language for Visual Reasoning
%A Suhr, Alane
%A Lewis, Mike
%A Yeh, James
%A Artzi, Yoav
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F suhr-etal-2017-corpus
%X We present a new visual reasoning language dataset, containing 92,244 pairs of examples of natural statements grounded in synthetic images with 3,962 unique sentences. We describe a method of crowdsourcing linguistically-diverse data, and present an analysis of our data. The data demonstrates a broad set of linguistic phenomena, requiring visual and set-theoretic reasoning. We experiment with various models, and show the data presents a strong challenge for future research.
%R 10.18653/v1/P17-2034
%U https://aclanthology.org/P17-2034
%U https://doi.org/10.18653/v1/P17-2034
%P 217-223
Markdown (Informal)
[A Corpus of Natural Language for Visual Reasoning](https://aclanthology.org/P17-2034) (Suhr et al., ACL 2017)
ACL
- Alane Suhr, Mike Lewis, James Yeh, and Yoav Artzi. 2017. A Corpus of Natural Language for Visual Reasoning. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 217–223, Vancouver, Canada. Association for Computational Linguistics.