@inproceedings{kuhnle-copestake-2018-deep,
title = "Deep learning evaluation using deep linguistic processing",
author = "Kuhnle, Alexander and
Copestake, Ann",
editor = "Bisk, Yonatan and
Levy, Omer and
Yatskar, Mark",
booktitle = "Proceedings of the Workshop on Generalization in the Age of Deep Learning",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-1003/",
doi = "10.18653/v1/W18-1003",
pages = "17--23",
abstract = "We discuss problems with the standard approaches to evaluation for tasks like visual question answering, and argue that artificial data can be used to address these as a complement to current practice. We demonstrate that with the help of existing {\textquoteleft}deep' linguistic processing technology we are able to create challenging abstract datasets, which enable us to investigate the language understanding abilities of multimodal deep learning models in detail, as compared to a single performance value on a static and monolithic dataset."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kuhnle-copestake-2018-deep">
<titleInfo>
<title>Deep learning evaluation using deep linguistic processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Kuhnle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Copestake</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 Workshop on Generalization in the Age of Deep Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Bisk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Levy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Yatskar</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 discuss problems with the standard approaches to evaluation for tasks like visual question answering, and argue that artificial data can be used to address these as a complement to current practice. We demonstrate that with the help of existing ‘deep’ linguistic processing technology we are able to create challenging abstract datasets, which enable us to investigate the language understanding abilities of multimodal deep learning models in detail, as compared to a single performance value on a static and monolithic dataset.</abstract>
<identifier type="citekey">kuhnle-copestake-2018-deep</identifier>
<identifier type="doi">10.18653/v1/W18-1003</identifier>
<location>
<url>https://aclanthology.org/W18-1003/</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>17</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deep learning evaluation using deep linguistic processing
%A Kuhnle, Alexander
%A Copestake, Ann
%Y Bisk, Yonatan
%Y Levy, Omer
%Y Yatskar, Mark
%S Proceedings of the Workshop on Generalization in the Age of Deep Learning
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F kuhnle-copestake-2018-deep
%X We discuss problems with the standard approaches to evaluation for tasks like visual question answering, and argue that artificial data can be used to address these as a complement to current practice. We demonstrate that with the help of existing ‘deep’ linguistic processing technology we are able to create challenging abstract datasets, which enable us to investigate the language understanding abilities of multimodal deep learning models in detail, as compared to a single performance value on a static and monolithic dataset.
%R 10.18653/v1/W18-1003
%U https://aclanthology.org/W18-1003/
%U https://doi.org/10.18653/v1/W18-1003
%P 17-23
Markdown (Informal)
[Deep learning evaluation using deep linguistic processing](https://aclanthology.org/W18-1003/) (Kuhnle & Copestake, Gen-Deep 2018)
ACL