# Unsupervised Post-processing of Word Vectors via Conceptor Negation

arXiv: https://arxiv.org/abs/1811.11001 · HTML: https://mlsanity.com/paper/1811.11001/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2018.

## Built on by (most cited first, 10 of 10)

- [Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token Embeddings](https://mlsanity.com/paper/2109.03127/) (2021)
- [Learning to Remove: Towards Isotropic Pre-trained BERT Embedding](https://mlsanity.com/paper/2104.05274/) (2021)
- [Just Rank: Rethinking Evaluation with Word and Sentence Similarities](https://mlsanity.com/paper/2203.02679/) (2022)
- [Conceptor-Aided Debiasing of Large Language Models](https://mlsanity.com/paper/2211.11087/) (2022)
- [One Swallow Does Not Make a Summer: Understanding Semantic Structures in Embedding Spaces](https://mlsanity.com/paper/2512.00852/) (2025)
- [Conceptors for Semantic Steering](https://mlsanity.com/paper/2605.04980/) (2026)
- [A Meta-embedding-based Ensemble Approach for ICD Coding Prediction](https://mlsanity.com/paper/2102.13622/) (2021)
- [On Isotropy Calibration of Transformers](https://mlsanity.com/paper/2109.13304/) (2021)
- [Conceptor Learning for Class Activation Mapping](https://mlsanity.com/paper/2201.08636/) (2022)
- [Frequency-aware Dimension Selection for Static Word Embedding by Mixed Product Distance](https://mlsanity.com/paper/2305.07826/) (2023)

## Abstract (arXiv)

Word vectors are at the core of many natural language processing tasks. Recently, there has been interest in post-processing word vectors to enrich their semantic information. In this paper, we introduce a novel word vector post-processing technique based on matrix conceptors (Jaeger2014), a family of regularized identity maps. More concretely, we propose to use conceptors to suppress those latent features of word vectors having high variances. The proposed method is purely unsupervised: it does not rely on any corpus or external linguistic database. We evaluate the post-processed word vectors on a battery of intrinsic lexical evaluation tasks, showing that the proposed method consistently outperforms existing state-of-the-art alternatives. We also show that post-processed word vectors can be used for the downstream natural language processing task of dialogue state tracking, yielding improved results in different dialogue domains.