Answers are grounded in this paper and cite their sources.
We directly embed easily extractable discourse structure information (subsection, paragraph and text type) in a transformer-based Dutch event coreference resolution model in order to more explicitly provide it with structural information that is known to be important in coreferential relationships. Results show that integrating this type of knowledge leads to a significant improvement in CONLL F1 for within-document settings (+ 8.6\%) and a minor improvement for cross-document settings (+ 1.1\%).
No takes yet. Share an insight, caveat, or question.
Langhe et al. (2023) studied this question.