Final CFP: First workshop on Universal Dependencies

Event Notification Type: 
Call for Papers
Abbreviated Title: 
UDW 2017
Location: 
Conference Centre Wallenberg
Monday, 22 May 2017
State: 
Country: 
Sweden
City: 
Gothenburg
Contact: 
Marie-Catherine de Marneffe (co-chair), The Ohio State University, USA
Joakim Nivre (co-chair), Uppsala University, Sweden
Filip Ginter, University of Turku, Finland
Yoav Goldberg, Ben Gurion University, Israel
Sampo Pyysalo, University of Cambridge, UK
Sebastian Schuster, Stanford University, USA
Reut Tsarfaty, Open University of Israel, Israel
Francis Tyers, University of Tromsø, Norway
Submission Deadline: 
Monday, 20 March 2017

Universal Dependencies (UD) is a framework for cross-linguistically consistent treebank annotation that has so far been applied to over 50 languages.

The framework is aiming to capture similarities as well as idiosyncrasies among typologically different languages (e.g., morphologically rich languages, pro-drop languages, and languages featuring clitic doubling). The goal in developing UD was not only to support comparative evaluation and cross-lingual learning but also to facilitate multilingual natural language processing and enable comparative linguistic studies.

After a period of very rapid growth since the release of the first guidelines in October 2014, it is now time to take stock and reflect on the theory and practice of UD, its use in research and development, and its future goals and challenges.

The first workshop on Universal Dependencies is co-located with NoDaLiDa in Gothenburg, Sweden. We are excited to announce the following invited speakers:

  • Mirella Lapata (School of Informatics, University of Edinburgh)
  • William Croft (Department of Linguistics, University of New Mexico)

We invite papers on all topics relevant to UD, including but not limited to:

  • theoretical foundations and universal guidelines
  • linguistic analysis of specific languages and/or constructions
  • language typology and linguistic universals
  • treebank annotation, conversion and validation
  • word segmentation, morphological tagging and syntactic parsing
  • downstream applications in natural language processing

Priority will be given to papers that adopt a cross-lingual perspective.

We solicit two types of papers: regular workshop papers and cross-submissions. Papers will be presented as oral presentations or posters, but only regular workshop papers will be included in the proceedings published in the ACL Anthology, where no distinction will be made on the basis of mode of presentation.

The regular workshop papers can be long papers (maximum length of eight (8) pages of content) as well as short papers (maximum length of four (4) pages of content), and should report substantially original research. Reviews will be double-blind.

In addition to unpublished work, in the spirit of promoting discussion in the UD community, we also solicit papers on related topics that have already appeared elsewhere. The selection of these papers will solely be determined by the organizing committee.

Sponsors:

  • Google