[Corpora-List] Call for Participation: SemEval 2016 Task 10 - Detecting Minimal Semantic Units and their Meanings

Nathan Schneider nschneid at cs.cmu.edu
Mon Aug 31 16:16:32 CEST 2015


TL;DR There will be a lexical semantics shared task on tagging English sentences with multiword expressions + noun and verb supersenses.

First Call for Participation

Detecting Minimal Semantic Units and their Meanings

http://dimsum16.github.io/

as part of

SemEval-2016

International Workshop on Semantic Evaluation 2016

http://alt.qcri.org/semeval2016/

== Introduction ==

Are you into lexical semantics and up for a challenge? You should participate in SemEval's 2016 DiMSUM shared task! The task addresses two common problems in lexical semantics: identifying expressions spanning multiple words, and finding their broad semantic classes (i.e., supersenses).

Participating systems are expected to solve both aspects, but the manner in which they do this and the number of resources you use is up to you.

We provide gold standard training data labeled with multiwords and supersenses for two non-standard domains: online reviews and tweets. The test data will be in these two domains as well as a third, surprise domain.

To register, go to http://alt.qcri.org/semeval2016/task10/

== Data ==

The DiMSUM shared task at SemEval 2016 <http://alt.qcri.org/semeval2016/> is concerned with predicting, given an English sentence, a broad-coverage representation of lexical semantics. The representation consists of two closely connected facets: a segmentation into minimal semantic units, and a labeling of some of those units with semantic classes known as supersenses.

For example, given a POS-tagged sentence, the goal is to predict a representation like:

I googled(communication) restaurants(GROUP) in the area(LOCATION) and Fuji_Sushi(GROUP) came_up(communication) and reviews(COMMUNICATION) were( stative) great so I made_ a carry_out(possession) _order(communication)

where lowercase labels are verb supersenses, UPPERCASE labels are noun supersenses, and _ joins tokens within a multiword expression.

To read more and download the data, go to http://dimsum16.github.io/

== Task Organizers ==

Nathan Schneider, University of Edinburgh

Anders Johannsen, University of Copenhagen

Dirk Hovy, University of Copenhagen

Marine Carpuat, University of Maryland

== Important Dates ==

Trial data ready: June 30, 2015

Training data ready: September 8, 2015

Test data ready: December 15, 2015

Evaluation start: January 10, 2015

Evaluation end: January 31, 2015

Paper submission due: February 28, 2016 [TBC]

Paper reviews due: March 31, 2016 [TBC]

Camera ready due: April 30, 2016 [TBC]

SemEval workshop: Summer 2016

== Participants ==

If you are interested in participating, you should:

* Sign up on the Google Group at <https://groups.google.com/d/forum/clinical-tempeval> https://groups.google.com/group/dimsum16

* Begin developing your systems with the trial data available from <https://github.com/stylerw/thymedata/releases/tag/1.1.0%2Bcoloncancer-dev>

http://dimsum16.github.io/

If you have any further questions about the task, please post them to the Google Group where they will be answered by the organizers. -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 22754 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20150831/6094dfc9/attachment.txt>



More information about the Corpora mailing list