Papers with DensRay
Analytical Methods for Interpretable Ultradense Word Embeddings (D19-1)
Copied to clipboard
| Challenge: | Word embeddings lack interpretability, but rotation of word spaces can help . e.g., lexicon induction, gender bias can be removed by removing interpretable dimensions . |
| Approach: | They propose three methods for making word embeddings interpretable by rotation . they use Densifier, linear SVMs and DensRay to compute word spaces in closed form . |
| Outcome: | The proposed method can be computed in closed form and is more robust than Densifier. |
Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations (2020.coling-main)
Copied to clipboard
| Challenge: | Prior work identifies a linear gender subspace and removes gender information by eliminating the subspace. |
| Approach: | They propose to use DensRay to obtain interpretable dense subspaces by applying it to attention heads and layers of BERT. |
| Outcome: | The proposed method performs on-par with prior approaches, but is more robust and preserves language model performance better. |