back

Wikidata knowledge base completion using multilingual Wikipedia fact extraction

If you suspend your transcription on amara.org, please add a timestamp below to indicate how far you progressed! This will help others to resume your work!

Please do not press “publish” on amara.org to save your progress, use “save draft” instead. Only press “publish” when you're done with quality control.

Video duration
00:30:01
Language
English
Abstract
-

In this session we’ll talk about the SLING project at Google. The aim of the project is to learn to read and understand Wikipedia articles in many languages in terms existing knowledge, i.e., specific entities and properties in Wikidata. A key part of the project is that we use the same representation for both knowledge and document annotation, namely frame semantics. The Sling parser can be trained to produce frame semantic representations of text directly without any explicit intervening linguistic representation.
The project is a work in progress and we have built a number of the components needed, like the SLING frame store (for building and manipulating frame semantic graph structures) and the Wiki flow pipeline which can take a raw dump of Wikidata and convert this into one big frame graph loadable into memory for fast graph traversal. The SLING Python API provides easy access to all this information.

Talk ID
wikidatacon2019-1120
Event:
wikidatacon2019
Day
2
Room
Kleist
Start
3 p.m.
Duration
00:25:00
Track
None
Type of
Talk
Speaker
Anders Sandholm
Michael Ringgaard
Talk Slug & media link
wikidatacon2019-1120-wikidata_knowledge_base_completion_using_multilingual_wikipedia_fact_extraction
100.0% Checking done100.0%
0.0% Syncing done0.0%
0.0% Transcribing done0.0%
0.0% Nothing done yet0.0%
  

Work on this video on Amara!