Coreference Chains Categorization by Sequence Clustering

Silvia Federzoni, Lydia-Mai Ho-Dac, Cécile Fabre


Abstract
The diversity of coreference chains is usually tackled by means of global features (length, types and number of referring expressions, distance between them, etc.). In this paper, we propose a novel approach that provides a description of their composition in terms of sequences of expressions. To this end, we apply sequence analysis techniques to bring out the various strategies for introducing a referent and keeping it active throughout discourse. We discuss a first application of this method to a French written corpus annotated with coreference chains. We obtain clusters that are linguistically coherent and interpretable in terms of reference strategies and we demonstrate the influence of text genre and semantic type of the referent on chain composition.
Anthology ID:
2021.codi-main.5
Volume:
Proceedings of the 2nd Workshop on Computational Approaches to Discourse
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic and Online
Venues:
CODI | CRAC | EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
52–57
Language:
URL:
https://aclanthology.org/2021.codi-main.5
DOI:
10.18653/v1/2021.codi-main.5
Bibkey:
Cite (ACL):
Silvia Federzoni, Lydia-Mai Ho-Dac, and Cécile Fabre. 2021. Coreference Chains Categorization by Sequence Clustering. In Proceedings of the 2nd Workshop on Computational Approaches to Discourse, pages 52–57, Punta Cana, Dominican Republic and Online. Association for Computational Linguistics.
Cite (Informal):
Coreference Chains Categorization by Sequence Clustering (Federzoni et al., CODI 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.codi-main.5.pdf