Submissions/WikiFactMine - Enhancing Wikidata by Mining the Scientific Literature

This is an accepted submission for Wikimania 2017.

Submission no. 3031 Subject - TWD

Title of the submission: WikiFactMine - Enhancing Wikidata by Mining the Scientific Literature

Type of submission (lecture, panel, tutorial/workshop, roundtable discussion, lightning talk, poster, birds of a feather discussion): Lecture

Author of the submission: T Arrow (talk) 10:27, 4 April 2017 (UTC)[reply]

Language of presentation: English

E-mail address: tomcontentmine.org

Username: T Arrow

Country of origin: United Kingdom

Affiliation, if any (organisation, company etc.): ContentMine

Personal homepage or blog

Abstract (up to 300 words to describe your proposal)

An introduction to the work undertaken in the WikiFactMine Project[1]. This seeks to mine facts from the Open Access (OA) Literature and make them available for quick and easy inclusion into the Wikimedia ecosystem. We're running a pipeline on Wikimedia Labs which is downloading the newly published OA literature day by day from Europe PubMedCentral and extracting facts from these papers. We're then making these facts available via the wikifactmine API on tool labs.

This talk will include short introduction to using the wikifactmine-api[2] on tool labs. How to search for the most recent facts we've ingested as well as how to retrieve a list of facts pertaining to a particular Wikidata item. We hope by Wikimania to also be able to demonstrate how to search for facts from a particular set of papers, for example: the Zika Corpus generated by WikiCite.

Improving Wikidata will be done by (semi-)automatically creating statements for human's to add to Wikidata items. Find out about how you can use our tools to find statements to add and also find out about building dictionaries using Wikidata so we extract facts from topic areas you're interested in but we don't currently cover.

We'll also be explaining why we believe using (semi-)automated statement generation is a good thing and why we think it will improve the quality of Wikidata (and eventually the other Wikimedia projects) as a whole.

This talk is a natural successor to the talk given at Wikimania 2014 by Peter Murray-Rust[3] and shows how we've progressed in mining the Open Access literature since then.

What will attendees take away from this session?

Attendees will learn the basics of what is needed to build new tools on top of the work done by the WikiFactMine Project. It's also an introduction for Wikimedians who what to learn how they can use the tools already. Finally, it will help attendees (who may or may not have concerns) learn about (semi-)automated statement addition.

Theme of presentation: Technology, Interface & Infrastructure

For workshops and discussions, what level is the intended audience?: Intermediate

Length of session (if other than 25 minutes, specify how long): 25 minutes

Will you attend Wikimania if your submission is not accepted?: Yes

Slides or further information (optional)

WikiFactMine is funded by a Project Grant from the Wikimedia Foundation. It is organised and administered by ContentMine[4] the project Peter Murray-Rust was just founding as he gave his talk at Wikimania 2014.

Special requests: N/A

Interested attendees

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. (# ~~~~).