Göm menyn

Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies, 22 May, Gothenburg Sweden
Full text (pdf) Title_Pages
Marie-Catherine de Marneffe: The Ohio State University, USA Joakim Nivre: Uppsala University, Sweden Sebastian Schuster: Stanford University, USA
No. of pages:
Linköping Electronic Conference Proceedings
ISSN (print):
ISSN (online):
NEALT Proceedings Series
Linköping University Electronic Press, Linköpings universitet

These proceedings include the program and papers that are presented at the first workshop on Universal Dependencies, held in conjunction with NoDaLiDa in Gothenburg (Sweden) on May 22, 2017.

Universal Dependencies (UD) is a framework for cross-linguistically consistent treebank annotation that has so far been applied to over 50 languages (http://universaldependencies.org/). 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 rapid growth since the release of the first guidelines in October 2014 and the release of the second version of the guidelines in December 2016, we felt it was 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. We are returning to Gothenburg where UD, in its actual implementation, was born in the spring of 2014.

We received 29 submissions of which 24 were accepted. Submissions covered several topics: the workshop feature papers describing treebank conversion or creation, while others focus on resources useful for annotation; some work targets specific syntactic constructions and which analysis to adopt, sometimes with critiques of the choices made in UD; some papers exploit UD resources for parsing or downstream tasks, often in a cross-lingual setting, and others discuss the relation of UD to different frameworks.

We are honored to have two invited speakers: Mirella Lapata (School of Informatics, University of Edinburgh, Scotland), with a talk on “Universal Semantic Parsing”, and William Croft (Department of Linguistics, University of New Mexico, USA), speaking about “Using Typology to Develop Guidelines for Universal Dependencies”. Our invited speakers’ work target different aspects of UD: Mirella Lapata’s talk is an instance of how UD facilitates building downstream applications which can operate multilingually, whereas William Croft will address how UD and typological universals intersect.

We are grateful to the program committee, who worked hard and on a tight schedule to review the submissions and provided authors with valuable feedback. We thank Google, Inc. for its sponsorship which made it ossible to feature two invited talks. We also want to thank the organizing committee for their help; in particular Francis Tyers and Sebastian Schuster for their invaluable help with the conference software and these proceedings, as well as Sampo Pyysalo for setting up the website and providing immediate response for updating it.

We tried to set up the program to favor discussions, and we wish all participants a productive workshop!

Marie-Catherine de Marneffe and Joakim Nivre

Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies, 22 May, Gothenburg Sweden

Željko Agic
Cross-lingual Parser Selection for Low-resource Languages
[Abstract and Fulltext]

Lars Ahrenberg
Swedish Prepositions are not Pure Function Words
[Abstract and Fulltext]

Gosse Bouma, Gertjan van Noord
Increasing Return on Annotation Investment: the Automatic Construction of a Universal Dependency Treebank for Dutch
[Abstract and Fulltext]

Çagri Çöltekin, Ben Campbell, Erhard Hinrichs, Heike Telljohann
Converting the TüBa-D/Z Treebank of German to Universal Dependencies
[Abstract and Fulltext]

Peter Dirix, Liesbeth Augustinus, Daniel van Niekerk, Frank Van Eynde
Universal Dependencies for Afrikaans
[Abstract and Fulltext]

Kira Droganova, Daniel Zeman
Elliptic Constructions: Spotting Patterns in UD Treebanks
[Abstract and Fulltext]

Felix Hennig, Arne Köhn
Dependency Tree Transformation with Tree Transducers
[Abstract and Fulltext]

John Lee, Herman Leung, Keying Li
Towards Universal Dependencies for Learner Chinese
[Abstract and Fulltext]

Natalia Levshina
Communicative efficiency and syntactic predictability: A cross-linguistic study based on the Universal Dependencies corpora
[Abstract and Fulltext]

Kadri Muischnek, Kaili Müürisep
Estonian Copular and Existential Constructions as an UD Annotation Problem
[Abstract and Fulltext]

Joakim Nivre, Chiao-Ting Fang
Universal Dependency Evaluation
[Abstract and Fulltext]

Martin Popel, Zdenek Žabokrtský, Martin Vojtek
Udapi: Universal API for Universal Dependencies
[Abstract and Fulltext]

Prokopis Prokopidis, Haris Papageorgiou
Universal Dependencies for Greek
[Abstract and Fulltext]

Aarne Ranta, Prasanth Kolachina
From Universal Dependencies to Abstract Syntax
[Abstract and Fulltext]

Natalie Schluter, Željko Agic
Empirically Sampling Universal Dependencies
[Abstract and Fulltext]

Sebastian Schuster, Matthew Lamm, Christopher D. Manning
Gapping Constructions in Universal Dependencies v2
[Abstract and Fulltext]

Hajime Senuma, Akiko Aizawa
Toward Universal Dependencies for Ainu
[Abstract and Fulltext]

Miikka Silfverberg, Mans Hulden
Automatic Morpheme Segmentation and Labeling in Universal Dependencies Resources
[Abstract and Fulltext]

Guillaume Wisniewski, Ophélie Lacroix
A Systematic Comparison of Syntactic Representations of Dependency Parsing
[Abstract and Fulltext]

Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies, 22 May, Gothenburg Sweden

Marie-Catherine de Marneffe, Joakim Nivre, Sebastian Schuster
Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies, 22 May, Gothenburg Sweden
Note: the following are taken directly from CrossRef
No citations available at the moment

Responsible for this page: Peter Berkesand
Last updated: 2017-02-21