@inproceedings{tillmann-etal-2023-muted,
title = "Muted: Multilingual Targeted Offensive Speech Identification and Visualization",
author = "Tillmann, Christoph and
Trivedi, Aashka and
Rosenthal, Sara and
Borse, Santosh and
Zhang, Rong and
Sil, Avirup and
Bhattacharjee, Bishwaranjan",
editor = "Feng, Yansong and
Lefever, Els",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-demo.19",
doi = "10.18653/v1/2023.emnlp-demo.19",
pages = "229--236",
abstract = "Offensive language such as hate, abuse, and profanity (HAP) occurs in various content on the web. While previous work has mostly dealt with sentence level annotations, there have been a few recent attempts to identify offensive spans as well. We build upon this work and introduce MUTED, a system to identify multilingual HAP content by displaying offensive arguments and their targets using heat maps to indicate their intensity. MUTED can leverage any transformer-based HAP-classification model and its attention mechanism out-of-the-box to identify toxic spans, without further fine-tuning. In addition, we use the spaCy library to identify the specific targets and arguments for the words predicted by the attention heatmaps. We present the model{'}s performance on identifying offensive spans and their targets in existing datasets and present new annotations on German text. Finally, we demonstrate our proposed visualization tool on multilingual inputs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tillmann-etal-2023-muted">
<titleInfo>
<title>Muted: Multilingual Targeted Offensive Speech Identification and Visualization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Tillmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aashka</namePart>
<namePart type="family">Trivedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">Borse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avirup</namePart>
<namePart type="family">Sil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bishwaranjan</namePart>
<namePart type="family">Bhattacharjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yansong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Offensive language such as hate, abuse, and profanity (HAP) occurs in various content on the web. While previous work has mostly dealt with sentence level annotations, there have been a few recent attempts to identify offensive spans as well. We build upon this work and introduce MUTED, a system to identify multilingual HAP content by displaying offensive arguments and their targets using heat maps to indicate their intensity. MUTED can leverage any transformer-based HAP-classification model and its attention mechanism out-of-the-box to identify toxic spans, without further fine-tuning. In addition, we use the spaCy library to identify the specific targets and arguments for the words predicted by the attention heatmaps. We present the model’s performance on identifying offensive spans and their targets in existing datasets and present new annotations on German text. Finally, we demonstrate our proposed visualization tool on multilingual inputs.</abstract>
<identifier type="citekey">tillmann-etal-2023-muted</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-demo.19</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-demo.19</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>229</start>
<end>236</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Muted: Multilingual Targeted Offensive Speech Identification and Visualization
%A Tillmann, Christoph
%A Trivedi, Aashka
%A Rosenthal, Sara
%A Borse, Santosh
%A Zhang, Rong
%A Sil, Avirup
%A Bhattacharjee, Bishwaranjan
%Y Feng, Yansong
%Y Lefever, Els
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F tillmann-etal-2023-muted
%X Offensive language such as hate, abuse, and profanity (HAP) occurs in various content on the web. While previous work has mostly dealt with sentence level annotations, there have been a few recent attempts to identify offensive spans as well. We build upon this work and introduce MUTED, a system to identify multilingual HAP content by displaying offensive arguments and their targets using heat maps to indicate their intensity. MUTED can leverage any transformer-based HAP-classification model and its attention mechanism out-of-the-box to identify toxic spans, without further fine-tuning. In addition, we use the spaCy library to identify the specific targets and arguments for the words predicted by the attention heatmaps. We present the model’s performance on identifying offensive spans and their targets in existing datasets and present new annotations on German text. Finally, we demonstrate our proposed visualization tool on multilingual inputs.
%R 10.18653/v1/2023.emnlp-demo.19
%U https://aclanthology.org/2023.emnlp-demo.19
%U https://doi.org/10.18653/v1/2023.emnlp-demo.19
%P 229-236
Markdown (Informal)
[Muted: Multilingual Targeted Offensive Speech Identification and Visualization](https://aclanthology.org/2023.emnlp-demo.19) (Tillmann et al., EMNLP 2023)
ACL
- Christoph Tillmann, Aashka Trivedi, Sara Rosenthal, Santosh Borse, Rong Zhang, Avirup Sil, and Bishwaranjan Bhattacharjee. 2023. Muted: Multilingual Targeted Offensive Speech Identification and Visualization. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 229–236, Singapore. Association for Computational Linguistics.