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:
The invited speaker for the workshop will be Bonnie Webber (Institute for Language, Cognition, and Computation, University of Edinburgh) - title: TBA.
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.
Important Dates
Submissions should follow the two-column format of ACL Anthology proceedings and should be anonymized for double blind reviewing. NAACL offers both LaTeX style files and Microsof Word templates at:
https://naacl2019.org/calls/papers/
Papers should be submitted at:
https://www.softconf.com/naacl2019/disrpt/
As part of the efforts to improve diversity and inclusion in at the NAACL 2019 conference, we are pleased to offer a service that may help authors improve their workshop submissions. Grammarly is a program that checks your English writing and suggests corrections. We are providing free premium access to authors for one month. You may benefit especially if you are not a native English speaker or if you have other difficulties with writing or proofreading. Presenting your research in clear standard English can increase your paper's chances of getting good reviews and, if accepted, a wide audience.
To use this service, please fill out this form: https://bit.ly/2Ssp4Pq
You should receive an email with the premium access code and further instructions within one day.
We hope that this initiative will especially benefit non-native English speakers in the NLP community. We thank Grammarly for generously donating this service (at NACL’s request) and supporting diversity and inclusion in NLP!