# Analytical Methods for Interpretable Ultradense Word Embeddings

arXiv: https://arxiv.org/abs/1904.08654 · HTML: https://mlsanity.com/paper/1904.08654/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2019.

## Built on by (most cited first, 13 of 13)

- [A Survey on Gender Bias in Natural Language Processing](https://mlsanity.com/paper/2112.14168/) (2021)
- [On the Explainability of Natural Language Processing Deep Models](https://mlsanity.com/paper/2210.06929/) (2022)
- [Cross-Entropy Is All You Need To Invert the Data Generating Process](https://mlsanity.com/paper/2410.21869/) (2024)
- [Interpreting Deep Learning Models in Natural Language Processing: A Review](https://mlsanity.com/paper/2110.10470/) (2021)
- [Fairness in Language Models Beyond English: Gaps and Challenges](https://mlsanity.com/paper/2302.12578/) (2023)
- [Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques](https://mlsanity.com/paper/2310.10310/) (2023)
- [Verb Conjugation in Transformers Is Determined by Linear Encodings of Subject Number](https://mlsanity.com/paper/2310.15151/) (2023)
- [Locating Language-Specific Information in Contextualized Embeddings](https://mlsanity.com/paper/2109.08040/) (2021)
- [Interpreting Embedding Spaces by Conceptualization](https://mlsanity.com/paper/2209.00445/) (2022)
- [One Swallow Does Not Make a Summer: Understanding Semantic Structures in Embedding Spaces](https://mlsanity.com/paper/2512.00852/) (2025)
- [Explainability of Text Processing and Retrieval Methods: A Survey](https://mlsanity.com/paper/2212.07126/) (2022)
- [Dialectograms: Machine Learning Differences between Discursive Communities](https://mlsanity.com/paper/2302.05657/) (2023)
- [Optimal synthesis embeddings](https://mlsanity.com/paper/2406.10259/) (2024)

## Abstract (arXiv)

Word embeddings are useful for a wide variety of tasks, but they lack interpretability. By rotating word spaces, interpretable dimensions can be identified while preserving the information contained in the embeddings without any loss. In this work, we investigate three methods for making word spaces interpretable by rotation: Densifier (Rothe et al., 2016), linear SVMs and DensRay, a new method we propose. In contrast to Densifier, DensRay can be computed in closed form, is hyperparameter-free and thus more robust than Densifier. We evaluate the three methods on lexicon induction and set-based word analogy. In addition we provide qualitative insights as to how interpretable word spaces can be used for removing gender bias from embeddings.