Abstract
This paper describes the process of adapting the Stanford Coreference resolution module to the Basque language, taking into account the characteristics of the language. The module has been integrated in a linguistic analysis pipeline obtaining an end-to-end coreference resolution system for the Basque language. The adaptation process explained can benefit and facilitate other languages with similar characteristics in the implementation of their coreference resolution systems. During the experimentation phase, we have demonstrated that language-specific features have a noteworthy effect on coreference resolution, obtaining a gain in CoNLL score of 7.07 with respect to the baseline system. We have also analysed the effect that preprocessing has in coreference resolution, comparing the results obtained with automatic mentions versus gold mentions. When gold mentions are provided, the results increase 11.5 points in CoNLL score in comparison with results obtained when automatic mentions are used. The contribution of each sieve is analysed concluding that morphology is essential for agglutinative languages to obtain good performance in coreference resolution. Finally, an error analysis of the coreference resolution system is presented which have revealed our system’s weak points and help to determine the improvements of the system. As a result of the error analysis, we have enriched the Basque coreference resolution adding new two sieves, obtaining an improvement of 0.24 points in CoNLL F1 when automatic mentions are used and of 0.39 points when the gold mentions are provided.
Highlights
Coreference resolution consists of identifying textual expressions that refer to realworld objects and determining which of these mentions refer to the same entity
Much attention has been paid to the problem of coreference resolution and many evaluation campaigns focusing on the topic have been undertaken in the last decades, from MUC-6 [3] in 1995 to the CoNLL shared task in 2012 [4]
EUSKOR outperforms the baseline system according to F1 on all the metrics
Summary
Coreference resolution consists of identifying textual expressions (mentions) that refer to realworld objects (entities) and determining which of these mentions refer to the same entity. It is complex to create completely language-independent systems, whereas taking into account the characteristics of a language benefits performance of these tasks. In this scenario, a possible solution is to use a state-of-the-art system with a flexible modular architecture and adapt it to resolve coreference in the new language to be treated. The process we carried out demonstrates that using a modular architecture facilitates the development of robust coreference resolution systems for any language with different characteristics to the language for which the system was originally created. We describe the most important characteristics of Basque and the challenges they present for coreference resolution.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.