@inproceedings{lu-etal-2018-entity,
title = "Entity-aware Image Caption Generation",
author = "Lu, Di and
Whitehead, Spencer and
Huang, Lifu and
Ji, Heng and
Chang, Shih-Fu",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1435",
doi = "10.18653/v1/D18-1435",
pages = "4013--4023",
abstract = "Current image captioning approaches generate descriptions which lack specific information, such as named entities that are involved in the images. In this paper we propose a new task which aims to generate informative image captions, given images and hashtags as input. We propose a simple but effective approach to tackle this problem. We first train a convolutional neural networks - long short term memory networks (CNN-LSTM) model to generate a template caption based on the input image. Then we use a knowledge graph based collective inference algorithm to fill in the template with specific named entities retrieved via the hashtags. Experiments on a new benchmark dataset collected from Flickr show that our model generates news-style image descriptions with much richer information. Our model outperforms unimodal baselines significantly with various evaluation metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2018-entity">
<titleInfo>
<title>Entity-aware Image Caption Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spencer</namePart>
<namePart type="family">Whitehead</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifu</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shih-Fu</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current image captioning approaches generate descriptions which lack specific information, such as named entities that are involved in the images. In this paper we propose a new task which aims to generate informative image captions, given images and hashtags as input. We propose a simple but effective approach to tackle this problem. We first train a convolutional neural networks - long short term memory networks (CNN-LSTM) model to generate a template caption based on the input image. Then we use a knowledge graph based collective inference algorithm to fill in the template with specific named entities retrieved via the hashtags. Experiments on a new benchmark dataset collected from Flickr show that our model generates news-style image descriptions with much richer information. Our model outperforms unimodal baselines significantly with various evaluation metrics.</abstract>
<identifier type="citekey">lu-etal-2018-entity</identifier>
<identifier type="doi">10.18653/v1/D18-1435</identifier>
<location>
<url>https://aclanthology.org/D18-1435</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>4013</start>
<end>4023</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entity-aware Image Caption Generation
%A Lu, Di
%A Whitehead, Spencer
%A Huang, Lifu
%A Ji, Heng
%A Chang, Shih-Fu
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F lu-etal-2018-entity
%X Current image captioning approaches generate descriptions which lack specific information, such as named entities that are involved in the images. In this paper we propose a new task which aims to generate informative image captions, given images and hashtags as input. We propose a simple but effective approach to tackle this problem. We first train a convolutional neural networks - long short term memory networks (CNN-LSTM) model to generate a template caption based on the input image. Then we use a knowledge graph based collective inference algorithm to fill in the template with specific named entities retrieved via the hashtags. Experiments on a new benchmark dataset collected from Flickr show that our model generates news-style image descriptions with much richer information. Our model outperforms unimodal baselines significantly with various evaluation metrics.
%R 10.18653/v1/D18-1435
%U https://aclanthology.org/D18-1435
%U https://doi.org/10.18653/v1/D18-1435
%P 4013-4023
Markdown (Informal)
[Entity-aware Image Caption Generation](https://aclanthology.org/D18-1435) (Lu et al., EMNLP 2018)
ACL
- Di Lu, Spencer Whitehead, Lifu Huang, Heng Ji, and Shih-Fu Chang. 2018. Entity-aware Image Caption Generation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4013–4023, Brussels, Belgium. Association for Computational Linguistics.