1 citations · 2 across the 5 of their papers we have counts for
5 papers
Bipol: A Novel Multi-Axes Bias Evaluation Metric with Explainability for NLP
Lama Alkhaled, Tosin Adewumi, Sana Sabah Sabry
We introduce bipol, a new metric with explainability, for estimating social bias in text data. Harmful bias is prevalent in many online sources of data that are used for training m…
Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets
Tosin Adewumi, Isabella Södergren, Lama Alkhaled +3
We investigate five English NLP benchmark datasets (on the superGLUE leaderboard) and two Swedish datasets for bias, along multiple axes. The datasets are the following: Boolean Qu…
T5 for Hate Speech, Augmented Data and Ensemble
Tosin Adewumi, Sana Sabah Sabry, Nosheen Abid +2
We conduct relatively extensive investigations of automatic hate speech (HS) detection using different state-of-the-art (SoTA) baselines over 11 subtasks of 6 different datasets. O…
HaT5: Hate Language Identification using Text-to-Text Transfer Transformer
Sana Sabah Sabry, Tosin Adewumi, Nosheen Abid +3
We investigate the performance of a state-of-the art (SoTA) architecture T5 (available on the SuperGLUE) and compare with it 3 other previous SoTA architectures across 5 different…
Småprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning
Tosin Adewumi, Rickard Brännvall, Nosheen Abid +4
Building open-domain conversational systems (or chatbots) that produce convincing responses is a recognized challenge. Recent state-of-the-art (SoTA) transformer-based models for t…