Journal's Facebook pageNeural Coreference Resolution for Slovene Language
- University of Ljubljana, Faculty of Computer and Information Science
Večna pot 113, 1000 Ljubljana
matej.klemen@fri.uni-lj.si, slavko.zitnik@fri.uni-lj.si
Abstract
Coreference resolution systems aim to recognize and cluster together mentions of the same underlying entity. While there exist large amounts of research on broadly spoken languages such as English and Chinese, research on coreference in other languages is comparably scarce. In this work we first present SentiCoref 1.0 - a coreference resolution dataset for Slovene language that is comparable to English-based corpora. Further, we conduct a series of analyses using various complex models that range from simple linear models to current state-of-the-art deep neural coreference approaches leveraging pre-trained contextual embeddings. Apart from SentiCoref, we evaluate models also on a smaller coref149 Slovene dataset to justify the creation of a new corpus. We investigate robustness of the models using cross-domain data and data augmentations. Models using contextual embeddings achieve the best results - up to 0.92 average F 1 score for the SentiCoref dataset. Cross-domain experiments indicate that SentiCoref allows the models to learn more general patterns, which enables them to outperform models, learned on coref149 only.
Key words
coreference resolution, Slovene language, neural networks, word embeddings
Digital Object Identifier (DOI)
https://doi.org/10.2298/CSIS201120060K
Publication information
Volume 19, Issue 2 (June 2022)
Year of Publication: 2022
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium
Full text
Available in PDF
Portable Document Format
How to cite
Klemen, M., Žitnik, S.: Neural Coreference Resolution for Slovene Language. Computer Science and Information Systems, Vol. 19, No. 2, 495–521. (2022), https://doi.org/10.2298/CSIS201120060K
