Multilingual segmentation based on neural networks and pre-trained word embeddings

Mikel Iruskieta, Kepa Bengoetxea, Aitziber Atutxa Salazar, Arantza Diaz de Ilarraza


Abstract
The DISPRT 2019 workshop has organized a shared task aiming to identify cross-formalism and multilingual discourse segments. Elementary Discourse Units (EDUs) are quite similar across different theories. Segmentation is the very first stage on the way of rhetorical annotation. Still, each annotation project adopted several decisions with consequences not only on the annotation of the relational discourse structure but also at the segmentation stage. In this shared task, we have employed pre-trained word embeddings, neural networks (BiLSTM+CRF) to perform the segmentation. We report F1 results for 6 languages: Basque (0.853), English (0.919), French (0.907), German (0.913), Portuguese (0.926) and Spanish (0.868 and 0.769). Finally, we also pursued an error analysis based on clause typology for Basque and Spanish, in order to understand the performance of the segmenter.
Anthology ID:
W19-2716
Volume:
Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019
Month:
June
Year:
2019
Address:
Minneapolis, MN
Venues:
NAACL | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
125–132
Language:
URL:
https://aclanthology.org/W19-2716
DOI:
10.18653/v1/W19-2716
Bibkey:
Cite (ACL):
Mikel Iruskieta, Kepa Bengoetxea, Aitziber Atutxa Salazar, and Arantza Diaz de Ilarraza. 2019. Multilingual segmentation based on neural networks and pre-trained word embeddings. In Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019, pages 125–132, Minneapolis, MN. Association for Computational Linguistics.
Cite (Informal):
Multilingual segmentation based on neural networks and pre-trained word embeddings (Iruskieta et al., 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-2716.pdf
Software:
 W19-2716.Software.pdf
Data
DISRPT2019