@inproceedings{nishimura-etal-2019-procedural,
title = "Procedural Text Generation from a Photo Sequence",
author = "Nishimura, Taichi and
Hashimoto, Atsushi and
Mori, Shinsuke",
editor = "van Deemter, Kees and
Lin, Chenghua and
Takamura, Hiroya",
booktitle = "Proceedings of the 12th International Conference on Natural Language Generation",
month = oct # "{--}" # nov,
year = "2019",
address = "Tokyo, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-8650",
doi = "10.18653/v1/W19-8650",
pages = "409--414",
abstract = "Multimedia procedural texts, such as instructions and manuals with pictures, support people to share how-to knowledge. In this paper, we propose a method for generating a procedural text given a photo sequence allowing users to obtain a multimedia procedural text. We propose a single embedding space both for image and text enabling to interconnect them and to select appropriate words to describe a photo. We implemented our method and tested it on cooking instructions, i.e., recipes. Various experimental results showed that our method outperforms standard baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishimura-etal-2019-procedural">
<titleInfo>
<title>Procedural Text Generation from a Photo Sequence</title>
</titleInfo>
<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">Atsushi</namePart>
<namePart type="family">Hashimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinsuke</namePart>
<namePart type="family">Mori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-oct–nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kees</namePart>
<namePart type="family">van Deemter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenghua</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimedia procedural texts, such as instructions and manuals with pictures, support people to share how-to knowledge. In this paper, we propose a method for generating a procedural text given a photo sequence allowing users to obtain a multimedia procedural text. We propose a single embedding space both for image and text enabling to interconnect them and to select appropriate words to describe a photo. We implemented our method and tested it on cooking instructions, i.e., recipes. Various experimental results showed that our method outperforms standard baselines.</abstract>
<identifier type="citekey">nishimura-etal-2019-procedural</identifier>
<identifier type="doi">10.18653/v1/W19-8650</identifier>
<location>
<url>https://aclanthology.org/W19-8650</url>
</location>
<part>
<date>2019-oct–nov</date>
<extent unit="page">
<start>409</start>
<end>414</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Procedural Text Generation from a Photo Sequence
%A Nishimura, Taichi
%A Hashimoto, Atsushi
%A Mori, Shinsuke
%Y van Deemter, Kees
%Y Lin, Chenghua
%Y Takamura, Hiroya
%S Proceedings of the 12th International Conference on Natural Language Generation
%D 2019
%8 oct–nov
%I Association for Computational Linguistics
%C Tokyo, Japan
%F nishimura-etal-2019-procedural
%X Multimedia procedural texts, such as instructions and manuals with pictures, support people to share how-to knowledge. In this paper, we propose a method for generating a procedural text given a photo sequence allowing users to obtain a multimedia procedural text. We propose a single embedding space both for image and text enabling to interconnect them and to select appropriate words to describe a photo. We implemented our method and tested it on cooking instructions, i.e., recipes. Various experimental results showed that our method outperforms standard baselines.
%R 10.18653/v1/W19-8650
%U https://aclanthology.org/W19-8650
%U https://doi.org/10.18653/v1/W19-8650
%P 409-414
Markdown (Informal)
[Procedural Text Generation from a Photo Sequence](https://aclanthology.org/W19-8650) (Nishimura et al., INLG 2019)
ACL
- Taichi Nishimura, Atsushi Hashimoto, and Shinsuke Mori. 2019. Procedural Text Generation from a Photo Sequence. In Proceedings of the 12th International Conference on Natural Language Generation, pages 409–414, Tokyo, Japan. Association for Computational Linguistics.