[PDF][PDF] Haspeede 2@ evalita2020: Overview of the evalita 2020 hate speech detection task
Abstract The Hate Speech Detection (HaSpeeDe 2) task is the second edition of a shared
task on the detection of hateful content in Italian Twitter messages. HaSpeeDe 2 is …
task on the detection of hateful content in Italian Twitter messages. HaSpeeDe 2 is …
[PDF][PDF] AMI@ EVALITA2020: Automatic misogyny identification
Automatic Misogyny Identification (AMI) is a shared task proposed at the Evalita 2020
evaluation campaign. The AMI challenge, based on Italian tweets, is organized into two …
evaluation campaign. The AMI challenge, based on Italian tweets, is organized into two …
Entropy-based attention regularization frees unintended bias mitigation from lists
Natural Language Processing (NLP) models risk overfitting to specific terms in the training
data, thereby reducing their performance, fairness, and generalizability. Eg, neural hate …
data, thereby reducing their performance, fairness, and generalizability. Eg, neural hate …
Lost in translation: large language models in non-English content analysis
G Nicholas, A Bhatia - arxiv preprint arxiv:2306.07377, 2023 - arxiv.org
In recent years, large language models (eg, Open AI's GPT-4, Meta's LLaMa, Google's
PaLM) have become the dominant approach for building AI systems to analyze and …
PaLM) have become the dominant approach for building AI systems to analyze and …
[PDF][PDF] Benchmarking post-hoc interpretability approaches for transformer-based misogyny detection
Warning: This paper contains examples of language that some people may find offensive.
Transformer-based Natural Language Processing models have become the standard for …
Transformer-based Natural Language Processing models have become the standard for …
Capturing covertly toxic speech via crowdsourcing
We study the task of labeling covert or veiled toxicity in online conversations. Prior research
has highlighted the difficulty in creating language models that recognize nuanced toxicity …
has highlighted the difficulty in creating language models that recognize nuanced toxicity …
[PDF][PDF] MilaNLP at semeval-2022 task 5: Using perceiver IO for detecting misogynous memes with text and image modalities
Warning: This paper contains examples of language that some people may find offensive or
upsetting. In this paper, we describe the system proposed by the MilaNLP team for the …
upsetting. In this paper, we describe the system proposed by the MilaNLP team for the …
HATE-ITA: Hate speech detection in Italian social media text
Online hate speech is a dangerous phenomenon that can (and should) be promptly
counteracted properly. While Natural Language Processing supplies appropriate algorithms …
counteracted properly. While Natural Language Processing supplies appropriate algorithms …
Misogyny and aggressiveness tend to come together and together we address them
A Muti, F Fernicola… - Proceedings of the …, 2022 - aclanthology.org
We target the complementary binary tasks of identifying whether a tweet is misogynous and,
if that is the case, whether it is also aggressive. We compare two ways to address these …
if that is the case, whether it is also aggressive. We compare two ways to address these …
A checkpoint on multilingual misogyny identification
A Muti, A Barrón-Cedeño - … of the 60th Annual Meeting of the …, 2022 - aclanthology.org
We address the problem of identifying misogyny in tweets in mono and multilingual settings
in three languages: English, Italian, and Spanish. We explore model variations considering …
in three languages: English, Italian, and Spanish. We explore model variations considering …