@inproceedings{yang-etal-2021-journalistic,
title = "Journalistic Guidelines Aware News Image Captioning",
author = "Yang, Xuewen and
Karaman, Svebor and
Tetreault, Joel and
Jaimes, Alejandro",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.419",
doi = "10.18653/v1/2021.emnlp-main.419",
pages = "5162--5175",
abstract = "The task of news article image captioning aims to generate descriptive and informative captions for news article images. Unlike conventional image captions that simply describe the content of the image in general terms, news image captions follow journalistic guidelines and rely heavily on named entities to describe the image content, often drawing context from the whole article they are associated with. In this work, we propose a new approach to this task, motivated by caption guidelines that journalists follow. Our approach, Journalistic Guidelines Aware News Image Captioning (JoGANIC), leverages the structure of captions to improve the generation quality and guide our representation design. Experimental results, including detailed ablation studies, on two large-scale publicly available datasets show that JoGANIC substantially outperforms state-of-the-art methods both on caption generation and named entity related metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2021-journalistic">
<titleInfo>
<title>Journalistic Guidelines Aware News Image Captioning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuewen</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Svebor</namePart>
<namePart type="family">Karaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alejandro</namePart>
<namePart type="family">Jaimes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of news article image captioning aims to generate descriptive and informative captions for news article images. Unlike conventional image captions that simply describe the content of the image in general terms, news image captions follow journalistic guidelines and rely heavily on named entities to describe the image content, often drawing context from the whole article they are associated with. In this work, we propose a new approach to this task, motivated by caption guidelines that journalists follow. Our approach, Journalistic Guidelines Aware News Image Captioning (JoGANIC), leverages the structure of captions to improve the generation quality and guide our representation design. Experimental results, including detailed ablation studies, on two large-scale publicly available datasets show that JoGANIC substantially outperforms state-of-the-art methods both on caption generation and named entity related metrics.</abstract>
<identifier type="citekey">yang-etal-2021-journalistic</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.419</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.419</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>5162</start>
<end>5175</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Journalistic Guidelines Aware News Image Captioning
%A Yang, Xuewen
%A Karaman, Svebor
%A Tetreault, Joel
%A Jaimes, Alejandro
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F yang-etal-2021-journalistic
%X The task of news article image captioning aims to generate descriptive and informative captions for news article images. Unlike conventional image captions that simply describe the content of the image in general terms, news image captions follow journalistic guidelines and rely heavily on named entities to describe the image content, often drawing context from the whole article they are associated with. In this work, we propose a new approach to this task, motivated by caption guidelines that journalists follow. Our approach, Journalistic Guidelines Aware News Image Captioning (JoGANIC), leverages the structure of captions to improve the generation quality and guide our representation design. Experimental results, including detailed ablation studies, on two large-scale publicly available datasets show that JoGANIC substantially outperforms state-of-the-art methods both on caption generation and named entity related metrics.
%R 10.18653/v1/2021.emnlp-main.419
%U https://aclanthology.org/2021.emnlp-main.419
%U https://doi.org/10.18653/v1/2021.emnlp-main.419
%P 5162-5175
Markdown (Informal)
[Journalistic Guidelines Aware News Image Captioning](https://aclanthology.org/2021.emnlp-main.419) (Yang et al., EMNLP 2021)
ACL
- Xuewen Yang, Svebor Karaman, Joel Tetreault, and Alejandro Jaimes. 2021. Journalistic Guidelines Aware News Image Captioning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5162–5175, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.