End-to-end Multilingual Coreference Resolution with Headword Mention Representation
Ondřej Pražák, Miloslav Konopík · 2024
This paper describes our approach to the CRAC 2024 Shared Task on Multilingual Coreference Resolution.Our model is based on an endto-end coreference resolution system.Apart from joined multilingual training, we improved our results with headword mention representation and training large model mT5-xxl through LORA.We provide an analysis of the performance of our model.Our system ended up in 4 th place.Moreover, we reached the best performance on three datasets out of 21.