With billions of individual pages on the web providing information on almost every conceivable topic, we should have the ability to collect facts that answer almost every conceivable question. However, only a small fraction of this information is contained in structured sources (Wikidata, Freebase, etc.) – we are therefore limited by our ability to transform free-form text to structured knowledge. There is, however, another problem that has become the focus of a lot of recent research and media coverage: false information coming from unreliable sources. [1] [2]
The FEVER workshops are a venue for work in verifiable knowledge extraction and to stimulate progress in this direction.
In order to bring together researchers working on the various tasks related to fact extraction and verification, we will host a workshop welcoming submissions on related topics such as recognizing textual entailment, question answering and argumentation mining.
All deadlines are calculated at 11:59pm Pacific Daylight Savings Time (UTC -7h).
Join the Slack Group for chat and updates: https://fever2018.slack.com.
Data can be downloaded and submissions evaluated on the Codalab competition page https://competitions.codalab.org/competitions/18814.
The shared task guidelines are available on the task page.
A simple baseline described in this NAACL2018 paper preprint, the scorer code, as well as the annotation UI source code are available on our GitHub page.
We will open the blind test set for scoring in July and accept system description papers on Softconf for the workshop at EMNLP2018. More details to follow soon.
The softconf submission page for Shared Task system descriptions and workshop papers is https://www.softconf.com/emnlp2018/FEVER.