Wembedder: Wikidata entity embedding web service
arXiv:1710.04099v126 citations
Originality Synthesis-oriented
AI Analysis
This provides a practical tool for researchers and developers working with Wikidata, but it is incremental as it applies existing methods to this specific dataset.
The authors tackled the problem of providing accessible embeddings for Wikidata entities by developing a web service that offers multilingual embeddings for over 600,000 items and properties, using Word2Vec on a graph walk.
I present a web service for querying an embedding of entities in the Wikidata knowledge graph. The embedding is trained on the Wikidata dump using Gensim's Word2Vec implementation and a simple graph walk. A REST API is implemented. Together with the Wikidata API the web service exposes a multilingual resource for over 600'000 Wikidata items and properties.