@inproceedings{liu-etal-2022-multiple,
title = "Multiple Instance Learning for Offensive Language Detection",
author = "Liu, Jiexi and
Kong, Dehan and
Huang, Longtao and
Mao, Dinghui and
Xue, Hui",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.546/",
doi = "10.18653/v1/2022.findings-emnlp.546",
pages = "7387--7396",
abstract = "Automatic offensive language detection has become a crucial issue in recent years. Existing researches on this topic are usually based on a large amount of data annotated at sentence level to train a robust model. However, sentence-level annotations are expensive in practice as the scenario expands, while there exist a large amount of natural labels from historical information on online platforms such as reports and punishments. Notably, these natural labels are usually in bag-level corresponding to the whole documents (articles, user profiles, conversations, etc.). Therefore, we target at proposing an approach capable of utilizing the bag-level labeled data for offensive language detection in this study. For this purpose, we formalize this task into a multiple instance learning (MIL) problem. We break down the design of existing MIL methods and propose a hybrid fusion MIL model with mutual-attention mechanism. In order to verify the validity of the proposed method, we present two new bag-level labeled datasets for offensive language detection: OLID-bags and MINOR. Experimental results based on the proposed datasets demonstrate the effectiveness of the mutual-attention method at both sentence level and bag level."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2022-multiple">
<titleInfo>
<title>Multiple Instance Learning for Offensive Language Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiexi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dehan</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longtao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dinghui</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic offensive language detection has become a crucial issue in recent years. Existing researches on this topic are usually based on a large amount of data annotated at sentence level to train a robust model. However, sentence-level annotations are expensive in practice as the scenario expands, while there exist a large amount of natural labels from historical information on online platforms such as reports and punishments. Notably, these natural labels are usually in bag-level corresponding to the whole documents (articles, user profiles, conversations, etc.). Therefore, we target at proposing an approach capable of utilizing the bag-level labeled data for offensive language detection in this study. For this purpose, we formalize this task into a multiple instance learning (MIL) problem. We break down the design of existing MIL methods and propose a hybrid fusion MIL model with mutual-attention mechanism. In order to verify the validity of the proposed method, we present two new bag-level labeled datasets for offensive language detection: OLID-bags and MINOR. Experimental results based on the proposed datasets demonstrate the effectiveness of the mutual-attention method at both sentence level and bag level.</abstract>
<identifier type="citekey">liu-etal-2022-multiple</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.546</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.546/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>7387</start>
<end>7396</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multiple Instance Learning for Offensive Language Detection
%A Liu, Jiexi
%A Kong, Dehan
%A Huang, Longtao
%A Mao, Dinghui
%A Xue, Hui
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F liu-etal-2022-multiple
%X Automatic offensive language detection has become a crucial issue in recent years. Existing researches on this topic are usually based on a large amount of data annotated at sentence level to train a robust model. However, sentence-level annotations are expensive in practice as the scenario expands, while there exist a large amount of natural labels from historical information on online platforms such as reports and punishments. Notably, these natural labels are usually in bag-level corresponding to the whole documents (articles, user profiles, conversations, etc.). Therefore, we target at proposing an approach capable of utilizing the bag-level labeled data for offensive language detection in this study. For this purpose, we formalize this task into a multiple instance learning (MIL) problem. We break down the design of existing MIL methods and propose a hybrid fusion MIL model with mutual-attention mechanism. In order to verify the validity of the proposed method, we present two new bag-level labeled datasets for offensive language detection: OLID-bags and MINOR. Experimental results based on the proposed datasets demonstrate the effectiveness of the mutual-attention method at both sentence level and bag level.
%R 10.18653/v1/2022.findings-emnlp.546
%U https://aclanthology.org/2022.findings-emnlp.546/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.546
%P 7387-7396
Markdown (Informal)
[Multiple Instance Learning for Offensive Language Detection](https://aclanthology.org/2022.findings-emnlp.546/) (Liu et al., Findings 2022)
ACL
- Jiexi Liu, Dehan Kong, Longtao Huang, Dinghui Mao, and Hui Xue. 2022. Multiple Instance Learning for Offensive Language Detection. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 7387–7396, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.