The 16th International Conference on Parsing Technologies (IWPT 2020)

July 9, 2020
Seattle, WA, USA


The ACL Special Interest Group on Natural Language Parsing (SIGPARSE) invites submissions to its biennial conference on parsing technologies. IWPT 2020 will be the 16th conference in a series that started in 1989. The conference will be held as a co-located ACL event on July 9, 2020, in Seattle, USA.



The IWPT 2020 Shared Task will be on Multilingual Parsing into Enhanced Universal Dependencies (EUD). In recent years, Universal Dependencies (UD)—the de-facto standard target representations in surface-syntactic dependency parsing—have grown a second layer of structure, called enhanced dependencies, where grammatical relations that cannot be adequately represented in pure rooted trees are encoded, for example control relations and argument sharing in relative clauses, shared dependencies involving coordinate structures, and dependencies involving ellipsis. Enhanced dependencies call for non-tree graphs with reentrancies, cycles, and empty nodes.

Data for the shared task consists of at least the treebanks in UD release 2.5 that contain enhanced annotation, and potentially EUD annotations for one or more additional languages. The task will be parsing from raw strings into EUD (according to the UD 2.5 guidelines). Evaluation will measure performance per phenomenon and will take into account the fact that not all treebanks cover all of the phenomena listed in the EUD guidelines.

The IWPT 2020 Shared Task maintains its own schedule and submission rules. For full details, please seee


Submit your paper through the following submission page:

IWPT addresses all aspects of structural analysis of natural language, including but not limited to:

  • Parsing of natural language (phonological, morphological, syntactic, semantic, discourse, etc.)
  • Formal models and algorithms for recognition, parsing and transduction
  • Machine learning techniques for syntax and parsing
  • Complexity of languages, models and algorithms
  • Learning of recursive structure (linguistic/latent)
  • Parsing in machine translation (synchronous parsing; alignment by parsing; translation by parsing, etc.)
  • Cognitive models of language processing
  • Multilingual and multimodal perspectives on syntax and parsing
  • Domain and genre adaptation, portability and robustness of parsing systems
  • Practical applications of parsing technology
  • Parser evaluation (across languages and frameworks)

For IWPT 2020, we particularly encourage submissions on the following topics, targeted to advance our understanding of how to apply deep learning most effectively for the structural analysis of natural languages:

  • Neural Network Models for linguistic structure predictions
  • Combining distributional and symbolic signals for linguistic structure prediction
  • Multilingual and Universal Parsing, Parsing typologically different languages
  • Parsing low-resource languages and cross-lingual or domain transfer
  • Unblackboxing deep learning models to probe their level of linguistic analysis
  • Integrating morphology via character-based models, subword embeddings, and beyond

Paper submissions can be made in two distinct tracks:

  • regular papers on substantial, original, and unpublished research, including empirical evaluation results, where appropriate; and
  • short papers on smaller, focused contributions, work in progress, negative results, or opinion pieces.

Papers accepted for presentation at the conference will be included in the IWPT 2020 proceedings, which will be published by the ACL and included in the ACL Anthology.


  • April 24, 2020 (anywhere on Earth): Paper submission deadline
  • May 19, 2020: Notification of acceptance
  • May 27, 2020: Camera-Ready versions due
  • July 9, 2020: One-day conference


All submissions must follow the ACL 2020 guidelines. Style templates for LaTeX and Microsoft Word are available at the following web site.

Submissions must be anonymous, i.e. not reveal author(s) on the title page or through self-references. Papers must be submitted digitally, in PDF, and uploaded through the online conference system:

Paper submissions that violate either of these requirements will be returned without review.

The page limits for submissions are: up to nine pages of content for regular papers, and up to four pages of content for short papers; any additional number of pages can be used for bibliographic references.


  • Kenji Sagae (General Chair)
  • Weiwei Sun (Programme Co-Chair)
  • Anders S√łgaard (Programme Co-Chair)
  • Stephan Oepen (Publicity Chair)
  • Yuji Matsumoto
  • Reut Tsarfaty