@inproceedings{cirik-etal-2018-visual,
title = "Visual Referring Expression Recognition: What Do Systems Actually Learn?",
author = "Cirik, Volkan and
Morency, Louis-Philippe and
Berg-Kirkpatrick, Taylor",
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/N18-2123",
doi = "10.18653/v1/N18-2123",
pages = "781--787",
abstract = "We present an empirical analysis of state-of-the-art systems for referring expression recognition {--} the task of identifying the object in an image referred to by a natural language expression {--} with the goal of gaining insight into how these systems reason about language and vision. Surprisingly, we find strong evidence that even sophisticated and linguistically-motivated models for this task may ignore linguistic structure, instead relying on shallow correlations introduced by unintended biases in the data selection and annotation process. For example, we show that a system trained and tested on the input image without the input referring expression can achieve a precision of 71.2{\%} in top-2 predictions. Furthermore, a system that predicts only the object category given the input can achieve a precision of 84.2{\%} in top-2 predictions. These surprisingly positive results for what should be deficient prediction scenarios suggest that careful analysis of what our models are learning {--} and further, how our data is constructed {--} is critical as we seek to make substantive progress on grounded language tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cirik-etal-2018-visual">
<titleInfo>
<title>Visual Referring Expression Recognition: What Do Systems Actually Learn?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Volkan</namePart>
<namePart type="family">Cirik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis-Philippe</namePart>
<namePart type="family">Morency</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taylor</namePart>
<namePart type="family">Berg-Kirkpatrick</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 present an empirical analysis of state-of-the-art systems for referring expression recognition – the task of identifying the object in an image referred to by a natural language expression – with the goal of gaining insight into how these systems reason about language and vision. Surprisingly, we find strong evidence that even sophisticated and linguistically-motivated models for this task may ignore linguistic structure, instead relying on shallow correlations introduced by unintended biases in the data selection and annotation process. For example, we show that a system trained and tested on the input image without the input referring expression can achieve a precision of 71.2% in top-2 predictions. Furthermore, a system that predicts only the object category given the input can achieve a precision of 84.2% in top-2 predictions. These surprisingly positive results for what should be deficient prediction scenarios suggest that careful analysis of what our models are learning – and further, how our data is constructed – is critical as we seek to make substantive progress on grounded language tasks.</abstract>
<identifier type="citekey">cirik-etal-2018-visual</identifier>
<identifier type="doi">10.18653/v1/N18-2123</identifier>
<location>
<url>https://aclanthology.org/N18-2123</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>781</start>
<end>787</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visual Referring Expression Recognition: What Do Systems Actually Learn?
%A Cirik, Volkan
%A Morency, Louis-Philippe
%A Berg-Kirkpatrick, Taylor
%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 cirik-etal-2018-visual
%X We present an empirical analysis of state-of-the-art systems for referring expression recognition – the task of identifying the object in an image referred to by a natural language expression – with the goal of gaining insight into how these systems reason about language and vision. Surprisingly, we find strong evidence that even sophisticated and linguistically-motivated models for this task may ignore linguistic structure, instead relying on shallow correlations introduced by unintended biases in the data selection and annotation process. For example, we show that a system trained and tested on the input image without the input referring expression can achieve a precision of 71.2% in top-2 predictions. Furthermore, a system that predicts only the object category given the input can achieve a precision of 84.2% in top-2 predictions. These surprisingly positive results for what should be deficient prediction scenarios suggest that careful analysis of what our models are learning – and further, how our data is constructed – is critical as we seek to make substantive progress on grounded language tasks.
%R 10.18653/v1/N18-2123
%U https://aclanthology.org/N18-2123
%U https://doi.org/10.18653/v1/N18-2123
%P 781-787
Markdown (Informal)
[Visual Referring Expression Recognition: What Do Systems Actually Learn?](https://aclanthology.org/N18-2123) (Cirik et al., NAACL 2018)
ACL
- Volkan Cirik, Louis-Philippe Morency, and Taylor Berg-Kirkpatrick. 2018. Visual Referring Expression Recognition: What Do Systems Actually Learn?. 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 781–787, New Orleans, Louisiana. Association for Computational Linguistics.