Multilingual Coreference Resolution with Harmonized Annotations
This work addresses coreference resolution for multilingual NLP applications, but it is incremental as it adapts an existing method to a new dataset.
The paper tackles coreference resolution across six languages using the new CorefUD corpus, finding that harmonized annotations and multilingual models improve performance, especially for languages with limited data, with specific gains noted in Slavic languages.
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.