@inproceedings{sun-etal-2020-riva,
title = "{RIVA}: A Pre-trained Tweet Multimodal Model Based on Text-image Relation for Multimodal {NER}",
author = "Sun, Lin and
Wang, Jiquan and
Su, Yindu and
Weng, Fangsheng and
Sun, Yuxuan and
Zheng, Zengwei and
Chen, Yuanyi",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.168",
doi = "10.18653/v1/2020.coling-main.168",
pages = "1852--1862",
abstract = "Multimodal named entity recognition (MNER) for tweets has received increasing attention recently. Most of the multimodal methods used attention mechanisms to capture the text-related visual information. However, unrelated or weakly related text-image pairs account for a large proportion in tweets. Visual clues unrelated to the text would incur uncertain or even negative effects for multimodal model learning. In this paper, we propose a novel pre-trained multimodal model based on Relationship Inference and Visual Attention (RIVA) for tweets. The RIVA model controls the attention-based visual clues with a gate regarding the role of image to the semantics of text. We use a teacher-student semi-supervised paradigm to leverage a large unlabeled multimodal tweet corpus with a labeled data set for text-image relation classification. In the multimodal NER task, the experimental results show the significance of text-related visual features for the visual-linguistic model and our approach achieves SOTA performance on the MNER datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2020-riva">
<titleInfo>
<title>RIVA: A Pre-trained Tweet Multimodal Model Based on Text-image Relation for Multimodal NER</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiquan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yindu</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fangsheng</namePart>
<namePart type="family">Weng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxuan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zengwei</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanyi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal named entity recognition (MNER) for tweets has received increasing attention recently. Most of the multimodal methods used attention mechanisms to capture the text-related visual information. However, unrelated or weakly related text-image pairs account for a large proportion in tweets. Visual clues unrelated to the text would incur uncertain or even negative effects for multimodal model learning. In this paper, we propose a novel pre-trained multimodal model based on Relationship Inference and Visual Attention (RIVA) for tweets. The RIVA model controls the attention-based visual clues with a gate regarding the role of image to the semantics of text. We use a teacher-student semi-supervised paradigm to leverage a large unlabeled multimodal tweet corpus with a labeled data set for text-image relation classification. In the multimodal NER task, the experimental results show the significance of text-related visual features for the visual-linguistic model and our approach achieves SOTA performance on the MNER datasets.</abstract>
<identifier type="citekey">sun-etal-2020-riva</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.168</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.168</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1852</start>
<end>1862</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RIVA: A Pre-trained Tweet Multimodal Model Based on Text-image Relation for Multimodal NER
%A Sun, Lin
%A Wang, Jiquan
%A Su, Yindu
%A Weng, Fangsheng
%A Sun, Yuxuan
%A Zheng, Zengwei
%A Chen, Yuanyi
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F sun-etal-2020-riva
%X Multimodal named entity recognition (MNER) for tweets has received increasing attention recently. Most of the multimodal methods used attention mechanisms to capture the text-related visual information. However, unrelated or weakly related text-image pairs account for a large proportion in tweets. Visual clues unrelated to the text would incur uncertain or even negative effects for multimodal model learning. In this paper, we propose a novel pre-trained multimodal model based on Relationship Inference and Visual Attention (RIVA) for tweets. The RIVA model controls the attention-based visual clues with a gate regarding the role of image to the semantics of text. We use a teacher-student semi-supervised paradigm to leverage a large unlabeled multimodal tweet corpus with a labeled data set for text-image relation classification. In the multimodal NER task, the experimental results show the significance of text-related visual features for the visual-linguistic model and our approach achieves SOTA performance on the MNER datasets.
%R 10.18653/v1/2020.coling-main.168
%U https://aclanthology.org/2020.coling-main.168
%U https://doi.org/10.18653/v1/2020.coling-main.168
%P 1852-1862
Markdown (Informal)
[RIVA: A Pre-trained Tweet Multimodal Model Based on Text-image Relation for Multimodal NER](https://aclanthology.org/2020.coling-main.168) (Sun et al., COLING 2020)
ACL