@inproceedings{j-kurisinkel-etal-2021-coherent,
title = "Coherent and Concise Radiology Report Generation via Context Specific Image Representations and Orthogonal Sentence States",
author = "J Kurisinkel, Litton and
Aw, Ai Ti and
Chen, Nancy F",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-industry.31",
doi = "10.18653/v1/2021.naacl-industry.31",
pages = "246--254",
abstract = "Neural models for text generation are often designed in an end-to-end fashion, typically with zero control over intermediate computations, limiting their practical usability in downstream applications. In this work, we incorporate explicit means into neural models to ensure topical continuity, informativeness and content diversity of generated radiology reports. For the purpose we propose a method to compute image representations specific to each sentential context and eliminate redundant content by exploiting diverse sentence states. We conduct experiments to generate radiology reports from medical images of chest x-rays using MIMIC-CXR. Our model outperforms baselines by up to 18{\%} and 29{\%} respective in the evaluation for informativeness and content ordering respectively, relative on objective metrics and 16{\%} on human evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="j-kurisinkel-etal-2021-coherent">
<titleInfo>
<title>Coherent and Concise Radiology Report Generation via Context Specific Image Representations and Orthogonal Sentence States</title>
</titleInfo>
<name type="personal">
<namePart type="given">Litton</namePart>
<namePart type="family">J Kurisinkel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ai</namePart>
<namePart type="given">Ti</namePart>
<namePart type="family">Aw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural models for text generation are often designed in an end-to-end fashion, typically with zero control over intermediate computations, limiting their practical usability in downstream applications. In this work, we incorporate explicit means into neural models to ensure topical continuity, informativeness and content diversity of generated radiology reports. For the purpose we propose a method to compute image representations specific to each sentential context and eliminate redundant content by exploiting diverse sentence states. We conduct experiments to generate radiology reports from medical images of chest x-rays using MIMIC-CXR. Our model outperforms baselines by up to 18% and 29% respective in the evaluation for informativeness and content ordering respectively, relative on objective metrics and 16% on human evaluation.</abstract>
<identifier type="citekey">j-kurisinkel-etal-2021-coherent</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-industry.31</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-industry.31</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>246</start>
<end>254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Coherent and Concise Radiology Report Generation via Context Specific Image Representations and Orthogonal Sentence States
%A J Kurisinkel, Litton
%A Aw, Ai Ti
%A Chen, Nancy F.
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F j-kurisinkel-etal-2021-coherent
%X Neural models for text generation are often designed in an end-to-end fashion, typically with zero control over intermediate computations, limiting their practical usability in downstream applications. In this work, we incorporate explicit means into neural models to ensure topical continuity, informativeness and content diversity of generated radiology reports. For the purpose we propose a method to compute image representations specific to each sentential context and eliminate redundant content by exploiting diverse sentence states. We conduct experiments to generate radiology reports from medical images of chest x-rays using MIMIC-CXR. Our model outperforms baselines by up to 18% and 29% respective in the evaluation for informativeness and content ordering respectively, relative on objective metrics and 16% on human evaluation.
%R 10.18653/v1/2021.naacl-industry.31
%U https://aclanthology.org/2021.naacl-industry.31
%U https://doi.org/10.18653/v1/2021.naacl-industry.31
%P 246-254
Markdown (Informal)
[Coherent and Concise Radiology Report Generation via Context Specific Image Representations and Orthogonal Sentence States](https://aclanthology.org/2021.naacl-industry.31) (J Kurisinkel et al., NAACL 2021)
ACL