Wikidata:WikidataCon 2017/Submissions/Wembedder: Wikidata entity embedding web service
This is an Open submission for WikidataCon 2017 that has not yet been reviewed by the members of the Program Committee.
- Submission no. 72
- Title of the submission
- Wembedder: Wikidata entity embedding web service
- Author(s) of the submission
- Finn Årup Nielsen (fnielsen)
- E-mail address
- faan@dtu.dk
- Country of origin
- Denmark
- Affiliation, if any (organisation, company etc.)
- Technical University of Denmark
- Type of session
- Demo
- Length of session
- 10 minutes.
- Ideal number of attendees
- Any
- EtherPad for documentation
- https://etherpad.wikimedia.org/p/WikidataCon-72
- Abstract
embedding (Q29043227) is a topic that has gained a considerable attention in the machine learning community in recent years. Wikidata as a corpus is often used to train the embedding models that can be used in a variety of applications. I have been experimenting with using Wikidata as the corpus for training the graph embedding (Q32081746) models and implemented a web service running with a JSON-based API on the Wikimedia Toolforge https://tools.wmflabs.org/wembedder/. The current version returns "most similar" Wikidata items based on a query item. Albeit the performance is not optimal, there seems to be great opportunities with embedding models with future Wikidata-for-Wiktionary and the combination of Wikidata and Wikipedia in a combined model.
- What will attendees take away from this session?
- Knowledge about how Wikidata data can be used with machine learning tools, particularly graph embedding
- Slides or further information
- Slides: Wembedder
- Short article: Wembedder: Wikidata entity embedding web service
- Special requests
Interested attendees
editIf you are interested in attending this session, please sign with your username below. This will help reviewers to decide which sessions are of high interest.