Skip to content
conftrace_
2023 ACL ACL 2023

Leveraging Structural Discourse Information for Event Coreference Resolution in Dutch

Abstract

AbstractWe 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\%).

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Loic De Langhe, Orphee De Clercq, Véronique Hoste

Topics

Artificial Intelligence > Learning Paradigms > Transfer Learning Deep Learning > Architectures > Transformers Natural Language Processing > Understanding > Coreference Resolution Natural Language Processing > Resources & Methods > Multilingual NLP Machine Learning > Learning Types > Deep Learning

Keywords

event coreference resolution discourse structure cross-document resolution within-document resolution cross-document coreference neural coreference dutch language transformer model within-document setting
Download PDF

More from ACL 2023

All ACL 2023 papers →
A Side-by-side Comparison of Transformers for Implicit Discourse Relation Classification
Ensemble Transfer Learning for Multilingual Coreference Resolution
Contrastive Hierarchical Discourse Graph for Scientific Document Summarization
Entity Coreference and Co-occurrence Aware Argument Mining from Biomedical Literature
A Weakly-Supervised Learning Approach to the Identification of “Alternative Lexicalizations” in Shallow Discourse Parsing
Entity-based SpanCopy for Abstractive Summarization to Improve the Factual Consistency