Exploring self-distillation based relational reasoning training for document-level relation extraction

L Zhang, J Su, Z Min, Z Miao, Q Hu, B Fu… - Proceedings of the …, 2023 - ojs.aaai.org
Document-level relation extraction (RE) aims to extract relational triples from a document.
One of its primary challenges is to predict implicit relations between entities, which are not …

End-to-end Learning of Logical Rules for Enhancing Document-level Relation Extraction

K Qi, J Du, H Wan - Proceedings of the 62nd Annual Meeting of …, 2024 - aclanthology.org
Document-level relation extraction (DocRE) aims to extract relations between entities in a
whole document. One of the pivotal challenges of DocRE is to capture the intricate …

Doctime: A document-level temporal dependency graph parser

P Mathur, V Morariu, V Kaynig-Fittkau… - Proceedings of the …, 2022 - aclanthology.org
We introduce DocTime-a novel temporal dependency graph (TDG) parser that takes as input
a text document and produces a temporal dependency graph. It outperforms previous BERT …

Coarse-to-fine knowledge graph domain adaptation based on distantly-supervised iterative training

H Cai, W Liao, Z Liu, Y Zhang, X Huang, S Ding… - arxiv preprint arxiv …, 2022 - arxiv.org
Modern supervised learning neural network models require a large amount of manually
labeled data, which makes the construction of domain-specific knowledge graphs time …