@inproceedings{tanaka-etal-2022-image,
title = "Image Description Dataset for Language Learners",
author = "Tanaka, Kento and
Nishimura, Taichi and
Nanjo, Hiroaki and
Shirai, Keisuke and
Kameko, Hirotaka and
Dantsuji, Masatake",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.735",
pages = "6814--6821",
abstract = "We focus on image description and a corresponding assessment system for language learners. To achieve automatic assessment of image description, we construct a novel dataset, the Language Learner Image Description (LLID) dataset, which consists of images, their descriptions, and assessment annotations. Then, we propose a novel task of automatic error correction for image description, and we develop a baseline model that encodes multimodal information from a learner sentence with an image and accurately decodes a corrected sentence. Our experimental results show that the developed model can revise errors that cannot be revised without an image.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tanaka-etal-2022-image">
<titleInfo>
<title>Image Description Dataset for Language Learners</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kento</namePart>
<namePart type="family">Tanaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taichi</namePart>
<namePart type="family">Nishimura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Nanjo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keisuke</namePart>
<namePart type="family">Shirai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hirotaka</namePart>
<namePart type="family">Kameko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masatake</namePart>
<namePart type="family">Dantsuji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We focus on image description and a corresponding assessment system for language learners. To achieve automatic assessment of image description, we construct a novel dataset, the Language Learner Image Description (LLID) dataset, which consists of images, their descriptions, and assessment annotations. Then, we propose a novel task of automatic error correction for image description, and we develop a baseline model that encodes multimodal information from a learner sentence with an image and accurately decodes a corrected sentence. Our experimental results show that the developed model can revise errors that cannot be revised without an image.</abstract>
<identifier type="citekey">tanaka-etal-2022-image</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.735</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6814</start>
<end>6821</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Image Description Dataset for Language Learners
%A Tanaka, Kento
%A Nishimura, Taichi
%A Nanjo, Hiroaki
%A Shirai, Keisuke
%A Kameko, Hirotaka
%A Dantsuji, Masatake
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F tanaka-etal-2022-image
%X We focus on image description and a corresponding assessment system for language learners. To achieve automatic assessment of image description, we construct a novel dataset, the Language Learner Image Description (LLID) dataset, which consists of images, their descriptions, and assessment annotations. Then, we propose a novel task of automatic error correction for image description, and we develop a baseline model that encodes multimodal information from a learner sentence with an image and accurately decodes a corrected sentence. Our experimental results show that the developed model can revise errors that cannot be revised without an image.
%U https://aclanthology.org/2022.lrec-1.735
%P 6814-6821
Markdown (Informal)
[Image Description Dataset for Language Learners](https://aclanthology.org/2022.lrec-1.735) (Tanaka et al., LREC 2022)
ACL
- Kento Tanaka, Taichi Nishimura, Hiroaki Nanjo, Keisuke Shirai, Hirotaka Kameko, and Masatake Dantsuji. 2022. Image Description Dataset for Language Learners. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 6814–6821, Marseille, France. European Language Resources Association.