Exploiting a lexical resource for discourse connective disambiguation in German

Peter Bourgonje, Manfred Stede


Abstract
In this paper we focus on connective identification and sense classification for explicit discourse relations in German, as two individual sub-tasks of the overarching Shallow Discourse Parsing task. We successively augment a purely-empirical approach based on contextualised embeddings with linguistic knowledge encoded in a connective lexicon. In this way, we improve over published results for connective identification, achieving a final F1-score of 87.93; and we introduce, to the best of our knowledge, first results for German sense classification, achieving an F1-score of 87.13. Our approach demonstrates that a connective lexicon can be a valuable resource for those languages that do not have a large PDTB-style-annotated coprus available.
Anthology ID:
2020.coling-main.505
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5737–5748
Language:
URL:
https://aclanthology.org/2020.coling-main.505
DOI:
10.18653/v1/2020.coling-main.505
Bibkey:
Cite (ACL):
Peter Bourgonje and Manfred Stede. 2020. Exploiting a lexical resource for discourse connective disambiguation in German. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5737–5748, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Exploiting a lexical resource for discourse connective disambiguation in German (Bourgonje & Stede, COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.505.pdf