Search Results for author:
Found 6 papers, 3 papers with code
Debiasing Sentence Embedders through Contrastive Word Pairs
It is problematic that most debiasing approaches are directly transferred from word embeddings, therefore these approaches fail to take into account the nonlinear nature of sentence embedders and the embeddings they produce.
Neural Architecture Search for Sentence Classification with BERT
Pre training of language models on large text corpora is common practice in Natural Language Processing.
Intelligent Learning Rate Distribution to reduce Catastrophic Forgetting in Transformers
We combine the learning rate distributions thus found and show that they generalize to better performance with respect to the problem of catastrophic forgetting.
Semantic Properties of cosine based bias scores for word embeddings
Furthermore, we formally analyze cosine based scores from the literature with regard to these requirements.
The SAME score: Improved cosine based bias score for word embeddings
Furthermore, we thoroughly investigate the existing cosine-based scores and their limitations in order to show why these scores fail to report biases in some situations.
Evaluating Metrics for Bias in Word Embeddings
However, lately some works have raised doubts about these metrics showing that even though such metrics report low biases, other tests still show biases.
