# EVE: Explainable Vector Based Embedding Technique Using Wikipedia

arXiv: https://arxiv.org/abs/1702.06891 · HTML: https://mlsanity.com/paper/1702.06891/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2017.

## Built on by (most cited first, 6 of 6)

- [Applications of Explainable AI for 6G: Technical Aspects, Use Cases, and Research Challenges](https://mlsanity.com/paper/2112.04698/) (2021)
- [Explainable machine learning multi-label classification of Spanish legal judgements](https://mlsanity.com/paper/2405.17610/) (2024)
- [Explainable Machine Learning for Breakdown Prediction in High Gradient RF Cavities](https://mlsanity.com/paper/2202.05610/) (2022)
- [LLM Online Spatial-temporal Signal Reconstruction Under Noise](https://mlsanity.com/paper/2411.15764/) (2024)
- [Adaptive Explainable Continual Learning Framework for Regression Problems with Focus on Power Forecasts](https://mlsanity.com/paper/2108.10781/) (2021)
- [Lex2vec: making Explainable Word Embeddings via Lexical Resources](https://mlsanity.com/paper/2103.02269/) (2021)

## Abstract (arXiv)

We present an unsupervised explainable word embedding technique, called EVE, which is built upon the structure of Wikipedia. The proposed model defines the dimensions of a semantic vector representing a word using human-readable labels, thereby it readily interpretable. Specifically, each vector is constructed using the Wikipedia category graph structure together with the Wikipedia article link structure. To test the effectiveness of the proposed word embedding model, we consider its usefulness in three fundamental tasks: 1) intruder detection - to evaluate its ability to identify a non-coherent vector from a list of coherent vectors, 2) ability to cluster - to evaluate its tendency to group related vectors together while keeping unrelated vectors in separate clusters, and 3) sorting relevant items first - to evaluate its ability to rank vectors (items) relevant to the query in the top order of the result. For each task, we also propose a strategy to generate a task-specific human-interpretable explanation from the model. These demonstrate the overall effectiveness of the explainable embeddings generated by EVE. Finally, we compare EVE with the Word2Vec, FastText, and GloVe embedding techniques across the three tasks, and report improvements over the state-of-the-art.