EVE: explainable vector based embedding technique using Wikipedia

@article{Qureshi2018EVEEV,
  title={EVE: explainable vector based embedding technique using Wikipedia},
  author={M. A. Qureshi and Derek Greene},
  journal={Journal of Intelligent Information Systems},
  year={2018},
  pages={1-29}
}
We present an unsupervised explainable vector embedding technique, called EVE, which is built upon the structure of Wikipedia. The proposed model defines the dimensions of a semantic vector representing a concept using human-readable labels, thereby it is 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 model, we consider its usefulness in… Expand
14 Citations
Explainable Recommendation based on Wikipedia Concept Vectors
  • PDF
Domain-specific meta-embedding with latent semantic structures
  • 1
Lex2vec: making Explainable Word Embedding via Distant Supervision
  • PDF
Towards Explainable Semantic Text Matching
  • 4
  • PDF
Explaining AI-based Decision Support Systems using Concept Localization Maps
  • 1
  • PDF
Understanding Legal Documents: Classification of Rhetorical Role of Sentences Using Deep Learning and Natural Language Processing
  • 1
Improving Semantic Search in the German Legal Domain with Word Embeddings
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 87 REFERENCES
A Latent Variable Model Approach to PMI-based Word Embeddings
  • 157
  • PDF
Knowledge Graph and Text Jointly Embedding
  • 287
  • PDF
RC-NET: A General Framework for Incorporating Knowledge into Word Representations
  • 169
  • Highly Influential
  • PDF
Glove: Global Vectors for Word Representation
  • 17,112
  • PDF
Vector Embedding of Wikipedia Concepts and Entities
  • 18
  • PDF
Distributional Memory: A General Framework for Corpus-Based Semantics
  • 583
  • PDF
Topical Word Embeddings
  • 303
  • PDF
Computing Semantic Relatedness Using Wikipedia-based Explicit Semantic Analysis
  • 2,241
  • PDF
...
1
2
3
4
5
...