Multilingual Coreference Resolution with Harmonized Annotations

07/26/2021
by   Ondřej Pražák, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset