Challenge: Existing work on document classification models mainly uses synthetic monolingual data without ground truth for author demographic attributes.
Approach: They assemble and publish a multilingual Twitter corpus for the task of hate speech detection using inferred author demographic factors.
Outcome: The results show that the classifiers learn human biases and can be discriminatory towards certain demographic groups.

Similar Papers

Social Bias in Multilingual Language Models: A Survey (2025.emnlp-main)

Copied to clipboard

Challenge: Pretrained multilingual models exhibit the same social bias as models processing English texts.
Approach: They examine the literature on bias evaluation and mitigation approaches in multilingual and non-English contexts and identify gaps in the field.
Outcome: The proposed models perform well on multilingual language understanding benchmarks and are consistent with the current literature.
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.
Easy Adaptation to Mitigate Gender Bias in Multilingual Text Classification (2022.naacl-main)

Copied to clipboard

Challenge: Existing approaches to mitigate demographic biases evaluate on monolingual data, however, multilingual data has not been examined.
Approach: They propose a standard domain adaptation model to reduce gender bias in multilingual contexts.
Outcome: The proposed model reduces gender bias and improves on two text classification tasks with three fair-aware baselines.
Comparative Evaluation of Label-Agnostic Selection Bias in Multilingual Hate Speech Datasets (2020.emnlp-main)

Copied to clipboard

Challenge: a recent study has shown that data collection is neglected by ignoring the quality of data.
Approach: They propose to use latent semantics to evaluate selection bias in hate speech . they compare latent Dirichlet Allocation (LDA) to eleven hate speech corpora .
Outcome: The proposed method could be revisable before focusing on classification performance.
The Challenges of Creating a Parallel Multilingual Hate Speech Corpus: An Exploration (2024.lrec-main)

Copied to clipboard

Challenge: Hate speech is one of the most demanding topics in Natural Language Processing, as its multifaceted nature is accompanied by a handful of challenges, such as multilinguality and cross-linguality.
Approach: They propose a pipeline that could be used to create a parallel multilingual hate speech dataset using machine translation.
Outcome: The proposed pipeline will be able to create a parallel multilingual hate speech dataset using machine translation.
Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages (2023.findings-acl)

Copied to clipboard

Challenge: Sentiment analysis systems are used in hundreds of products and languages . Gender and racial biases are well-studied in English, but understudied elsewhere .
Approach: They build a counterfactual evaluation corpus for gender and racial/migrant bias in four languages.
Outcome: The evaluation corpus reveals which models have less bias and pinpoints changes in model bias behaviour, enabling more targeted mitigation strategies.
Comparing Biases and the Impact of Multilingual Training across Multiple Languages (2023.emnlp-main)

Copied to clipboard

Challenge: Currently, studies on bias and fairness in natural language processing focus on a single language and/or across few attributes (e.g. gender, race). However, biases can manifest differently across languages for individual attributes.
Approach: They adapt existing sentiment bias templates in English to Italian, Chinese, Hebrew, and Spanish for race, religion, nationality, and gender.
Outcome: The proposed model favors groups that are dominant in each language's culture, indicating bias amplification, after multilingual finetuning.
On Evaluating and Mitigating Gender Biases in Multilingual Settings (2023.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks and resources for evaluating gender biases in multilingual settings are limited.
Approach: They propose to extend DisCo to different Indian languages using human annotations to evaluate gender biases in multilingual models.
Outcome: The proposed benchmarks and mitigation techniques are extended beyond English to evaluate gender biases in multilingual models.
Multilingual and Multi-Aspect Hate Speech Analysis (D19-1)

Copied to clipboard

Challenge: Current research on hate speech analysis is oriented towards monolingual and single classification tasks.
Approach: They propose to use a multilingual multi-aspect hate speech analysis dataset to test current methods . they evaluate the dataset in various classification settings and discuss how to leverage annotations .
Outcome: The proposed dataset can be used to improve hate speech detection and classification in general.
Artie Bias Corpus: An Open Dataset for Detecting Demographic Bias in Speech Applications (2020.lrec-1)

Copied to clipboard

Challenge: A speech technology exhibits demographic bias when performance is worse for one demographic group relative to another.
Approach: They create an English dataset of expert-validated audio, transcript> pairs with demographic tags for age, gender, accent and open software which may be used to detect demographic bias in Automatic Speech Recognition systems.
Outcome: The Artie Bias Corpus is a curated subset of the Mozilla Common Voice corpus, which is released under a Creative Commons CC0 license .

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