[Corpora-List] Discourse Relation Parsing and Treebanking (DISRPT 2019):Second call for papers and shared task

dasdebop dasdebop at hu-berlin.de
Tue Jan 22 10:26:44 CET 2019

(apologies for cross-postings)

Second Call for Papers and Shared Task - Discourse Relation Parsing and Treebanking (DISRPT 2019)

7th Workshop on Rhetorical Structure Theory and Related Formalisms In conjunction with: NAACL 2019, June 6


Study of coherence relations in frameworks such as RST, SDRT, and PDTB has experienced a revival in the last few years, in English and many other languages. Multiple sites are now actively engaged in the development of discourse parsers as a goal in itself, but also for applications such as sentiment analysis, argumentation mining, summarization, question answering, or machine translation evaluation. At the same time, evaluation of results in discourse parsing has proven complicated, and progress in integrating results across discourse treebanking frameworks has been slow.

DISRPT 2019 follows a series of biennial events on discourse relation studies, which were initially focused especially on RST. The 2019 workshop aims to broaden the scope of discussion to include different discourse theories (especially, but not limited to, RST, SDRT, and PDTB). We are interested in applied papers with a computational orientation, resource papers and work on discourse parsing, as well as papers that advance the field with novel theoretical contributions and promote cross-framework fertilization.

We invite submissions on the following and related topics, handling any language(s), and especially under-represented ones:

Discourse relations (segmentation, relation inventory, cognitive status of relations)

Discourse parsing in any formalism, including shallow and deep discourse parsing

Relation signaling (connectives and any other signals) and annotation

Applications of coherence relations in NLP

Invited Speaker

The invited speaker for the workshop will be Bonnie Webber (Institute for Language, Cognition, and Computation, University of Edinburgh) - title: TBA.

Shared Task - Discourse Unit Segmentation Across Formalisms

This workshop introduces the first iteration of a cross-formalism shared task on discourse unit segmentation. Since all major discourse parsing frameworks imply a segmentation of texts into segments, learning segmentations for and from diverse resources is a promising area for converging methods and insights. We will provide training, development and test datasets from all available languages in RST, SDRT, and PDTB, using a uniform format. Because different corpora, languages, and frameworks use different guidelines, the shared task will promote the design of flexible methods for dealing with various guidelines, and will help to push forward the discussion of converging standards for discourse units. For datasets which have treebanks, we will evaluate in two different scenarios: with and without gold syntax.

NOTE: The training data for the shared task has been released and is available at: https://github.com/disrpt/sharedtask2019.

Important Dates

Fri, Dec 28 - shared task sample data release

Mon, Jan 21 - training data release

Fri, Feb 15 - test data release

Thu, Feb 28 - papers due (shared task & regular workshop papers)

Wed, March 27 - notification of acceptance

Fri, April 5 - camera-ready papers due

June 6 - workshop


Amir Zeldes (Georgetown University, Washington, DC, USA) Debopam Das (Humboldt University of Berlin, Germany) Erick Galani Maziero (Universidade Federal de Lavras, Brazil) Juliano Desiderato Antonio (Universidade Estadual de MaringŠ, Brazil) Mikel Iruskieta (University of the Basque Country, Spain)

Program Committee

Stergos Afantenos, IRIT - Universitť Paul Sabatier, France Farah Benamara, IRIT - Universitť Paul Sabatier, France Irene Castellon, Universitat de Barcelona, Spain Johann Christian Chiarcos, Wolfgang Goethe Universitšt Frankfurt, Germany Maria Beatriz Nascimento Decat, Universidade Federal de Minas Gerais, Brazil Iria da Cunha, Universidad Nacional de Educaciůn a Distancia, Spain Barbara Di Eugenio, University of Illinois at Chicago, USA Arantza Diaz de Ilarraza, University of the Basque Country, Spain Flavius Frasincar, Erasmus University Rotterdam, Netherlands Maria Eduarda Giering, Universidade do Vale do Rio dos Sinos, Brazil Nancy Green, University of North Carolina, USA Graeme Hirst, University of Toronto, Canada Kerstin Kunz, Universitšt Heidelberg, Germany Ekaterina Lapshinova-Koltunski, Universitšt des Saarlandes, Germany Jiri Mirovsky, Charles University, Czech Republic Anna Nedoluzhko, Charles University, Czech Republic Thiago Pardo, Universidade de S„o Paulo, Brazil Lucie Polakova, Charles University, Czech Republic Gisela Redeker, University of Groningen, Netherlands Hannah Rohde, University of Edinburgh, UK Gerardo Sierra, Universidad Nacional Autůnoma de Mťxico, Mexico Christian Stab, Technische Universitšt Darmstadt, Germany Manfred Stede, Universitšt Potsdam, Germany Juan-Manuel Torres, Laboratoire Informatique d'Avignon, France Nianwen Xue, Brandeis University, USA

------------------------------------------------------------------------------------------------- -------------------------------------------------------------------------------------------------

Debopam Das Postdoctoral Researcher Department of English and American Studies Humboldt-Universitšt zu Berlin dasdebop at hu-berlin.de debdas at uni-potsdam.de; ddas at sfu.ca http://www.sfu.ca/~ddas

More information about the Corpora mailing list