We are pleased to announce the first shared task on parsing Discourse Representation Structures (DRSs). This shared task combines semantic role labelling, reference resolution, scope detection, named entity tagging, word sense disambiguation, predicate-argument structure prediction, presupposition projection --- yes, all of these! --- into one big challenge.
The DRSs are drawn from the Parallel Meaning Bank <http://pmb.let.rug.nl/>. In this first episode of DRS parsing we will test systems mainly on short, open-domain sentences, to make the threshold for participation as low as possible. A first data set is already available.
We will use CodaLab as interface for submission and access to data and tools. We also set up a task discussion group at Slack <https://drs-parsing.slack.com>. The outcome of the shared task and all participating systems will be presented at IWCS-2019 in Gothenburg <https://sites.google.com/view/iwcs2019/home>, Sweden (May 2019).
*Competition page*: https://competitions.codalab.org/competitions/20220 *Evaluation starts on February 25th, 2019*
Interested? At the competition page you find the schedule and a lot more information on the task. Any questions? Don't hesitate to contact us!
Organizers: Lasha Abzianidze, Johan Bos, Hessel Haagsma & Rik van Noord -- Lasha Abzianidze CLCG - Center for Language and Cognition University of Groningen -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 2170 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20181114/88078b79/attachment.txt>