Multi-lingual Discourse Segmentation and Connective Identification: MELODI at Disrpt2021

Morteza Kamaladdini Ezzabady, Philippe Muller, Chloé Braud


Abstract
We present an approach for discourse segmentation and discourse connective identification, both at the sentence and document level, within the Disrpt 2021 shared task, a multi-lingual and multi-formalism evaluation campaign. Building on the most successful architecture from the 2019 similar shared task, we leverage datasets in the same or similar languages to augment training data and improve on the best systems from the previous campaign on 3 out of 4 subtasks, with a mean improvement on all 16 datasets of 0.85%. Within the Disrpt 21 campaign the system ranks 3rd overall, very close to the 2nd system, but with a significant gap with respect to the best system, which uses a rich set of additional features. The system is nonetheless the best on languages that benefited from crosslingual training on sentence internal segmentation (German and Spanish).
Anthology ID:
2021.disrpt-1.3
Volume:
Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021)
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Amir Zeldes, Yang Janet Liu, Mikel Iruskieta, Philippe Muller, Chloé Braud, Sonia Badene
Venue:
DISRPT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
22–32
Language:
URL:
https://aclanthology.org/2021.disrpt-1.3
DOI:
10.18653/v1/2021.disrpt-1.3
Bibkey:
Cite (ACL):
Morteza Kamaladdini Ezzabady, Philippe Muller, and Chloé Braud. 2021. Multi-lingual Discourse Segmentation and Connective Identification: MELODI at Disrpt2021. In Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021), pages 22–32, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Multi-lingual Discourse Segmentation and Connective Identification: MELODI at Disrpt2021 (Kamaladdini Ezzabady et al., DISRPT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.disrpt-1.3.pdf
Software:
 2021.disrpt-1.3.Software.zip
Data
DISRPT2021