Arctic Knot Conference 2021/Submissions/Semi-automatic generation of relevant articles for the Basque Wikipedia
 | This is an open submission for the Arctic Knot Wikimedia Language Conference 2021. |
- Submission no.
- 3
- Title of the submission
- Semi-automatic generation of relevant articles for the Basque Wikipedia
- Author of the submission
- Joseba Fernandez de Landa, Rodrigo Agerri, Kepa Sarasola
- Submission format
- Pre-recorded video presentation (15–30 mins)
- Language of presentation
- English
- E-mail address
- joseba.fernandezdelanda
ehu.eus
- Country of origin
- Basque Country
- Affiliation, if any (organisation, company etc.)
- University of the Basque Country
- Personal homepage or blog
- Abstract (up to 300 words to describe your proposal)
The main objective of BasqueWikiNEE (Basque Wikipedia Name Entity Enrichment) is to identify in real-time those named entities that are most commented upon on Basque-language online media and that are not in Wikipedia yet. The annotation of named entities (people, institutions, or places) is performed using state-of-the-art deep learning models. Finally, the most frequent identified entities are published weekly in a Wikipedia page to display which entities do not currently have an article in the Basque Wikipedia.
https://eu.wikipedia.org/wiki/Wikiproiektu:Euskarazko_albisteetako_Izen_Entitateak
What kind of help could we offer to wikipedians in Basque when we know that suddenly a person has last week become known in the Basque media but he/she is not yet in the Basque Wikipedia?
First of all, we can check if that person is in Wikipedias of other languages, in the case of Basque its reference wikipedias (usual source for content translations) are those related to Catalan, Galizian, English, Spanish, and French. Links to the wikipedia articles in those languages may be useful for wikipedians who want to create the article in Basque using a general translation web service (elia.eus, Translate Google...), or the special service Content Translation provided by Wikimedia.
But there is a deeper contribution we can offer the user a draft (zirriborro) with the contents of minimal article that integrates basic data taken from Wikidata :(name, place of birth, year of birth, nationality, activity...), links (references) to the news extracted by our program, and some basic Wikipedia categories too.
https://github.com/joseba-fdl/Basque_wikipedia_enrich
- What will attendees take away from this session?
- Theme of session
- Language technology
- Slides or further information (optional)
- Special requests
- Is this Submission a Draft or Final?
- Draft
Interested attendees[edit]
If 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. Sign with a hash and four tildes. (# ~~~~).