Search Results for author:
Found 5 papers, 2 papers with code
Bipol: A Novel Multi-Axes Bias Evaluation Metric with Explainability for NLP
We introduce bipol, a new metric with explainability, for estimating social bias in text data.
Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets
Hence, we also contribute a new, large Swedish bias-labelled dataset (of 2 million samples), translated from the English version and train the SotA mT5 model on it.
T5 for Hate Speech, Augmented Data and Ensemble
Our motivation is to determine which of the recent SoTA models is best for automatic hate speech detection and what advantage methods like data augmentation and ensemble may have on the best model, if any.
HaT5: Hate Language Identification using Text-to-Text Transfer Transformer
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 tasks from 2 relatively diverse datasets.
Småprat: DialoGPT for Natural Language Generation of Swedish Dialogue by Transfer Learning
Perplexity score (an automated intrinsic language model metric) and surveys by human evaluation were used to assess the performances of the fine-tuned models, with results that indicate that the capacity for transfer learning can be exploited with considerable success.
