@inproceedings{lu-etal-2018-visual,
title = "Visual Attention Model for Name Tagging in Multimodal Social Media",
author = "Lu, Di and
Neves, Leonardo and
Carvalho, Vitor and
Zhang, Ning and
Ji, Heng",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-1185",
doi = "10.18653/v1/P18-1185",
pages = "1990--1999",
abstract = "Everyday billions of multimodal posts containing both images and text are shared in social media sites such as Snapchat, Twitter or Instagram. This combination of image and text in a single message allows for more creative and expressive forms of communication, and has become increasingly common in such sites. This new paradigm brings new challenges for natural language understanding, as the textual component tends to be shorter, more informal, and often is only understood if combined with the visual context. In this paper, we explore the task of name tagging in multimodal social media posts. We start by creating two new multimodal datasets: the first based on Twitter posts and the second based on Snapchat captions (exclusively submitted to public and crowd-sourced stories). We then propose a novel model architecture based on Visual Attention that not only provides deeper visual understanding on the decisions of the model, but also significantly outperforms other state-of-the-art baseline methods for this task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2018-visual">
<titleInfo>
<title>Visual Attention Model for Name Tagging in Multimodal Social Media</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">Leonardo</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vitor</namePart>
<namePart type="family">Carvalho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ning</namePart>
<namePart type="family">Zhang</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>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Everyday billions of multimodal posts containing both images and text are shared in social media sites such as Snapchat, Twitter or Instagram. This combination of image and text in a single message allows for more creative and expressive forms of communication, and has become increasingly common in such sites. This new paradigm brings new challenges for natural language understanding, as the textual component tends to be shorter, more informal, and often is only understood if combined with the visual context. In this paper, we explore the task of name tagging in multimodal social media posts. We start by creating two new multimodal datasets: the first based on Twitter posts and the second based on Snapchat captions (exclusively submitted to public and crowd-sourced stories). We then propose a novel model architecture based on Visual Attention that not only provides deeper visual understanding on the decisions of the model, but also significantly outperforms other state-of-the-art baseline methods for this task.</abstract>
<identifier type="citekey">lu-etal-2018-visual</identifier>
<identifier type="doi">10.18653/v1/P18-1185</identifier>
<location>
<url>https://aclanthology.org/P18-1185</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>1990</start>
<end>1999</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visual Attention Model for Name Tagging in Multimodal Social Media
%A Lu, Di
%A Neves, Leonardo
%A Carvalho, Vitor
%A Zhang, Ning
%A Ji, Heng
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F lu-etal-2018-visual
%X Everyday billions of multimodal posts containing both images and text are shared in social media sites such as Snapchat, Twitter or Instagram. This combination of image and text in a single message allows for more creative and expressive forms of communication, and has become increasingly common in such sites. This new paradigm brings new challenges for natural language understanding, as the textual component tends to be shorter, more informal, and often is only understood if combined with the visual context. In this paper, we explore the task of name tagging in multimodal social media posts. We start by creating two new multimodal datasets: the first based on Twitter posts and the second based on Snapchat captions (exclusively submitted to public and crowd-sourced stories). We then propose a novel model architecture based on Visual Attention that not only provides deeper visual understanding on the decisions of the model, but also significantly outperforms other state-of-the-art baseline methods for this task.
%R 10.18653/v1/P18-1185
%U https://aclanthology.org/P18-1185
%U https://doi.org/10.18653/v1/P18-1185
%P 1990-1999
Markdown (Informal)
[Visual Attention Model for Name Tagging in Multimodal Social Media](https://aclanthology.org/P18-1185) (Lu et al., ACL 2018)
ACL
- Di Lu, Leonardo Neves, Vitor Carvalho, Ning Zhang, and Heng Ji. 2018. Visual Attention Model for Name Tagging in Multimodal Social Media. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1990–1999, Melbourne, Australia. Association for Computational Linguistics.