@inproceedings{singh-2018-pushing,
title = "Pushing the Limits of Radiology with Joint Modeling of Visual and Textual Information",
author = "Singh, Sonit",
editor = "Shwartz, Vered and
Tabassum, Jeniya and
Voigt, Rob and
Che, Wanxiang and
de Marneffe, Marie-Catherine and
Nissim, Malvina",
booktitle = "Proceedings of {ACL} 2018, Student Research Workshop",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-3005",
doi = "10.18653/v1/P18-3005",
pages = "28--36",
abstract = "Recently, there has been increasing interest in the intersection of computer vision and natural language processing. Researchers have studied several interesting tasks, including generating text descriptions from images and videos and language embedding of images. More recent work has further extended the scope of this area to combine videos and language, learning to solve non-visual tasks using visual cues, visual question answering, and visual dialog. Despite a large body of research on the intersection of vision-language technology, its adaption to the medical domain is not fully explored. To address this research gap, we aim to develop machine learning models that can reason jointly on medical images and clinical text for advanced search, retrieval, annotation and description of medical images.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-2018-pushing">
<titleInfo>
<title>Pushing the Limits of Radiology with Joint Modeling of Visual and Textual Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sonit</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of ACL 2018, Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeniya</namePart>
<namePart type="family">Tabassum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">Voigt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malvina</namePart>
<namePart type="family">Nissim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, there has been increasing interest in the intersection of computer vision and natural language processing. Researchers have studied several interesting tasks, including generating text descriptions from images and videos and language embedding of images. More recent work has further extended the scope of this area to combine videos and language, learning to solve non-visual tasks using visual cues, visual question answering, and visual dialog. Despite a large body of research on the intersection of vision-language technology, its adaption to the medical domain is not fully explored. To address this research gap, we aim to develop machine learning models that can reason jointly on medical images and clinical text for advanced search, retrieval, annotation and description of medical images.</abstract>
<identifier type="citekey">singh-2018-pushing</identifier>
<identifier type="doi">10.18653/v1/P18-3005</identifier>
<location>
<url>https://aclanthology.org/P18-3005</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>28</start>
<end>36</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pushing the Limits of Radiology with Joint Modeling of Visual and Textual Information
%A Singh, Sonit
%Y Shwartz, Vered
%Y Tabassum, Jeniya
%Y Voigt, Rob
%Y Che, Wanxiang
%Y de Marneffe, Marie-Catherine
%Y Nissim, Malvina
%S Proceedings of ACL 2018, Student Research Workshop
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F singh-2018-pushing
%X Recently, there has been increasing interest in the intersection of computer vision and natural language processing. Researchers have studied several interesting tasks, including generating text descriptions from images and videos and language embedding of images. More recent work has further extended the scope of this area to combine videos and language, learning to solve non-visual tasks using visual cues, visual question answering, and visual dialog. Despite a large body of research on the intersection of vision-language technology, its adaption to the medical domain is not fully explored. To address this research gap, we aim to develop machine learning models that can reason jointly on medical images and clinical text for advanced search, retrieval, annotation and description of medical images.
%R 10.18653/v1/P18-3005
%U https://aclanthology.org/P18-3005
%U https://doi.org/10.18653/v1/P18-3005
%P 28-36
Markdown (Informal)
[Pushing the Limits of Radiology with Joint Modeling of Visual and Textual Information](https://aclanthology.org/P18-3005) (Singh, ACL 2018)
ACL