Planned intervention: On Wednesday June 26th 05:30 UTC Zenodo will be unavailable for 10-20 minutes to perform a storage cluster upgrade.
Natural Language Processing
Published November 3, 2020 | Version 1
Other Open

Tony French discourse segmentation model from Disrpt 2019 shared task

Creators

  • 1. University of Toulouse
  • 2. CNRS
  • 3. Datactivist

Description

Discourse segmentation model trained on French Annodis data, as made available by the Dirspt 2019 shared task 

https://sites.google.com/view/disrpt2019/shared-task

This model has to be used with the code available here: 

https://gitlab.inria.fr/andiamo/tony

The general model is described in 

Muller P, Braud C and Morey M , ToNy: Contextual embeddings for accurate multilingual discourse segmentation of full documents, In Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019. Minneapolis, MN, June, 2019., pp. 115-124. Association for Computational Linguistics.

 

 

Files

Files (662.7 MB)

Name Size Download all
md5:cbd2159d81624472c8cfa68948cf4e50
662.7 MB Download

Additional details

References

  • Muller P, Braud C and Morey M , ToNy: Contextual embeddings for accurate multilingual discourse segmentation of full documents, In Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019. Minneapolis, MN, June, 2019., pp. 115-124. Association for Computational Linguistics.