Multilingual Coreference Resolution with Harmonized Annotations

Ondřej Pražák and Miloslav Konopík and Jakub Sido
RANLP (2021)



In this paper, we present coreference resolution experiments with a newly created multilingual corpus CorefUD. We focus on the following languages: Czech, Russian, Polish, German, Spanish, and Catalan. In addition to monolingual experiments, we combine the training data in multilingual experiments and train two joined models -- for Slavic languages and for all the languages together. We rely on an end-to-end deep learning model that we slightly adapted for the CorefUD corpus. Our results show that we can profit from harmonized annotations, and using joined models helps significantly for the languages with smaller training data.



@inproceedings{pravzak2021multilingual, title={Multilingual Coreference Resolution with Harmonized Annotations}, author={Pra{\v{z}}{\'a}k, Ond{\v{r}}ej and Konop{\'\i}k, Miloslav and Sido, Jakub}, booktitle={Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)}, pages={1119--1123}, year={2021} }
Back to Top