@inproceedings{gohsen-etal-2023-paraphrase,
title = "Paraphrase Acquisition from Image Captions",
author = "Gohsen, Marcel and
Hagen, Matthias and
Potthast, Martin and
Stein, Benno",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.243/",
doi = "10.18653/v1/2023.eacl-main.243",
pages = "3348--3358",
abstract = "We propose to use image captions from the Web as a previously underutilized resource for paraphrases (i.e., texts with the same {\textquotedblleft}message{\textquotedblright}) and to create and analyze a corresponding dataset. When an image is reused on the Web, an original caption is often assigned. We hypothesize that different captions for the same image naturally form a set of mutual paraphrases. To demonstrate the suitability of this idea, we analyze captions in the English Wikipedia, where editors frequently relabel the same image for different articles. The paper introduces the underlying mining technology, the resulting Wikipedia-IPC dataset, and compares known paraphrase corpora with respect to their syntactic and semantic paraphrase similarity to our new resource. In this context, we introduce characteristic maps along the two similarity dimensions to identify the style of paraphrases coming from different sources. An annotation study demonstrates the high reliability of the algorithmically determined characteristic maps."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gohsen-etal-2023-paraphrase">
<titleInfo>
<title>Paraphrase Acquisition from Image Captions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcel</namePart>
<namePart type="family">Gohsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Hagen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Potthast</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benno</namePart>
<namePart type="family">Stein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose to use image captions from the Web as a previously underutilized resource for paraphrases (i.e., texts with the same “message”) and to create and analyze a corresponding dataset. When an image is reused on the Web, an original caption is often assigned. We hypothesize that different captions for the same image naturally form a set of mutual paraphrases. To demonstrate the suitability of this idea, we analyze captions in the English Wikipedia, where editors frequently relabel the same image for different articles. The paper introduces the underlying mining technology, the resulting Wikipedia-IPC dataset, and compares known paraphrase corpora with respect to their syntactic and semantic paraphrase similarity to our new resource. In this context, we introduce characteristic maps along the two similarity dimensions to identify the style of paraphrases coming from different sources. An annotation study demonstrates the high reliability of the algorithmically determined characteristic maps.</abstract>
<identifier type="citekey">gohsen-etal-2023-paraphrase</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.243</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.243/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>3348</start>
<end>3358</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Paraphrase Acquisition from Image Captions
%A Gohsen, Marcel
%A Hagen, Matthias
%A Potthast, Martin
%A Stein, Benno
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F gohsen-etal-2023-paraphrase
%X We propose to use image captions from the Web as a previously underutilized resource for paraphrases (i.e., texts with the same “message”) and to create and analyze a corresponding dataset. When an image is reused on the Web, an original caption is often assigned. We hypothesize that different captions for the same image naturally form a set of mutual paraphrases. To demonstrate the suitability of this idea, we analyze captions in the English Wikipedia, where editors frequently relabel the same image for different articles. The paper introduces the underlying mining technology, the resulting Wikipedia-IPC dataset, and compares known paraphrase corpora with respect to their syntactic and semantic paraphrase similarity to our new resource. In this context, we introduce characteristic maps along the two similarity dimensions to identify the style of paraphrases coming from different sources. An annotation study demonstrates the high reliability of the algorithmically determined characteristic maps.
%R 10.18653/v1/2023.eacl-main.243
%U https://aclanthology.org/2023.eacl-main.243/
%U https://doi.org/10.18653/v1/2023.eacl-main.243
%P 3348-3358
Markdown (Informal)
[Paraphrase Acquisition from Image Captions](https://aclanthology.org/2023.eacl-main.243/) (Gohsen et al., EACL 2023)
ACL
- Marcel Gohsen, Matthias Hagen, Martin Potthast, and Benno Stein. 2023. Paraphrase Acquisition from Image Captions. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3348–3358, Dubrovnik, Croatia. Association for Computational Linguistics.