Challenge: OLD is a less-resourced language regarding OLD.
Approach: They propose to annotate OLD in Modern Greek using the lexicon of offensive terms that originates from HurtLex.
Outcome: The proposed corpus is based on the lexicon of offensive terms that originates from HurtLex and can be used to detect offensive language in modern Greek.

Similar Papers

Offensive Language Identification in Greek (2020.lrec-1)

Copied to clipboard

Challenge: a gap in the literature on offensive language has been addressed with studies on Spanish, Hindi, and German.
Approach: They present a Greek annotated dataset for offensive language identification . it contains 4,779 tweets annotating offensive and not offensive posts from Twitter . they evaluate several computational models trained and tested on the dataset .
Outcome: The proposed dataset contains 4,779 tweets annotated as offensive and not offensive . the authors show that the proposed dataset is similar to the OLID dataset for English .
A Corpus of Turkish Offensive Language on Social Media (2020.lrec-1)

Copied to clipboard

Challenge: Identifying abusive, offensive, aggressive or in general inappropriate language has recently attracted interest of researchers from academic as well as commercial institutions.
Approach: They propose to classify Turkish offensive language corpus using state-of-the-art annotation methods . they find 19 % of tweets contain some type of offensive language .
Outcome: The proposed corpus of Turkish offensive language is the first of its kind in the world . the results show that 19 % of the tweets contain some type of offensive language .
OLEA: Tool and Infrastructure for Offensive Language Error Analysis in English (2023.eacl-demo)

Copied to clipboard

Challenge: State-of-the-art models for identifying offensive language fail to generalize over nuanced or implicit cases of offensive and hateful language.
Approach: They propose an open-source Python library for error analysis in the context of offensive language detection.
Outcome: OLEA provides tools for error analysis in the context of detecting offensive language in English.
Hate-Speech and Offensive Language Detection in Roman Urdu (2020.emnlp-main)

Copied to clipboard

Challenge: Existing research on hate-speech and offensive language detection in social media content is mainly focused on the English language.
Approach: They propose to use an annotated dataset to detect hate-speech and offensive language in social media content . they propose to transfer five existing embedding models to Roman Urdu to test their performance .
Outcome: The proposed model outperforms existing methods on RUHSOLD dataset and train domain-specific embeddings on more than 4.7 million tweets.
Offensive language detection in Hebrew: can other languages help? (2022.lrec-1)

Copied to clipboard

Challenge: Various approaches for offensive language detection have been applied for this task . contamination of social networks with offensive content is a new reality affecting almost all of us .
Approach: They propose to use multiple supervised models and text representations to detect offensive language in three languages, including two Semitic languages.
Outcome: The proposed model can detect offensive content in two Semitic languages, including Hebrew and Arabic, and it is able to perform cross-lingual and multilingual learning.
A Dataset of Offensive Language in Kosovo Social Media (2022.lrec-1)

Copied to clipboard

Challenge: Social media are a central part of people’s lives but are rife with bullying and offensive language, creating an unsafe environment for their users.
Approach: They propose to use user-generated comments on Facebook and YouTube from selected Kosovo news platforms to annotate offensive language in Albanian.
Outcome: The proposed system improves on Danish but not Albanian, on offensive language recognition and distinguishing targeted and untargeted offence.
CoRoSeOf - An Annotated Corpus of Romanian Sexist and Offensive Tweets (2022.lrec-1)

Copied to clipboard

Challenge: Using CoRoSeOf, we manually annotate social media for sexist and offensive language.
Approach: They introduce a large corpus of Romanian social media manually annotated for sexist and offensive language.
Outcome: The proposed corpus contains 39 245 tweets annotated by multiple annotators with an agreement rate of Fleiss’= 0.45 .
AGILe: The First Lemmatizer for Ancient Greek Inscriptions (2022.lrec-1)

Copied to clipboard

Challenge: Existing models for ancient Greek inscriptions are not performant on epigraphic data due to language differences . a lemmatizer for ancient inscription data can enable meaningful generalizations, we show .
Approach: They propose to train an automatic lemmatizer for ancient Greek inscriptions with 80% accuracy . they also show that existing models are not performant on epigraphic data .
Outcome: The proposed model achieves above 80% accuracy on epigraphic data, and makes it available to the community.
An Italian Twitter Corpus of Hate Speech against Immigrants (L18-1)

Copied to clipboard

Challenge: a recent study has annotated 6,000 tweets for hate speech against immigrants . the annotation scheme was designed to account for the multiplicity of factors that can contribute to the definition of a hate speech notion .
Approach: They describe a Twitter corpus annotated for hate speech against immigrants . they propose a scheme that includes aggressiveness, offensiveness, irony, stereotype and intensity .
Outcome: The proposed annotation scheme includes aggressiveness, offensiveness, irony, stereotype, intensity and (on an experimental basis) intensity.
On the Robustness of Offensive Language Classifiers (2022.acl-long)

Copied to clipboard

Challenge: Existing studies on offensive language classifiers have focused on primitive attacks such as misspellings and extraneous spaces.
Approach: They analyze the robustness of offensive language classifiers against crafty adversarial attacks that leverage greedy- and attention-based word selection and context-aware embeddings for word replacement.
Outcome: The proposed classifiers are robust against more crafty attacks that leverage greedy- and attention-based word selection and context-aware embeddings for word replacement.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations