Peerda: Data augmentation via modeling peer relation for span identification tasks

W Xu, X Li, Y Deng, W Lam, L Bing - arXiv preprint arXiv:2210.08855, 2022 - arxiv.org
Span identification aims at identifying specific text spans from text input and classifying them
into pre-defined categories. Different from previous works that merely leverage the …

DuRE: Dual Contrastive Self Training for Semi-Supervised Relation Extraction

Y Feng, L Lakshmanan - Proceedings of the 2024 Conference of …, 2024 - aclanthology.org
Abstract Document-level Relation Extraction (RE) aims to extract relation triples from
documents. Existing document-RE models typically rely on supervised learning which …

LogicST: A Logical Self-Training Framework for Document-Level Relation Extraction with Incomplete Annotations

S Fan, Y Wang, S Mo, J Niu - … of the 2024 Conference on Empirical …, 2024 - aclanthology.org
Document-level relation extraction (DocRE) aims to identify relationships between entities
within a document. Due to the vast number of entity pairs, fully annotating all fact triplets is …

VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extraction

KP Tran, W Hua, X Li - arXiv preprint arXiv:2412.13503, 2024 - arxiv.org
Document-level Relation Extraction (DocRE) aims to identify relationships between entity
pairs within a document. However, most existing methods assume a uniform label …

Towards alleviating human supervision for document-level relation extraction

Y Feng - 2024 - open.library.ubc.ca
Motivated by various downstream applications, there is tremendous interest in the automatic
construction of knowledge graphs (KG) by extracting relations from text corpora. Relation …