3 papers
cs.CL2024
The SAME score: Improved cosine based bias score for word embeddings
Sarah Schröder, Alexander Schulz, Barbara Hammer
With the enourmous popularity of large language models, many researchers have raised ethical concerns regarding social biases incorporated in such models. Several methods to measur…
cs.CL2024
Intelligent Learning Rate Distribution to reduce Catastrophic Forgetting in Transformers
Philip Kenneweg, Alexander Schulz, Sarah Schröder +1
Pretraining language models on large text corpora is a common practice in natural language processing. Fine-tuning of these models is then performed to achieve the best results on…
cs.CL2024
Debiasing Sentence Embedders through Contrastive Word Pairs
Philip Kenneweg, Sarah Schröder, Alexander Schulz +1
Over the last years, various sentence embedders have been an integral part in the success of current machine learning approaches to Natural Language Processing (NLP). Unfortunately…