Knowledge-Rich Temporal Relation Identification and Classification in Clinical Notes

DSpace/Manakin Repository

Knowledge-Rich Temporal Relation Identification and Classification in Clinical Notes

Show full item record

Title: Knowledge-Rich Temporal Relation Identification and Classification in Clinical Notes
Author(s):
D'Souza, Jennifer;
Ng, Vincent
Item Type: article
Keywords: Temporal relations
Semantic relations
Classification
Relation types
Abstract: Motivation: We examine the task of temporal relation classification for the clinical domain. Our approach to this task departs from existing ones in that it is (i) 'knowledge-rich', employing sophisticated knowledge derived from discourse relations as well as both domain-independent and domain-dependent semantic relations, and (ii) 'hybrid', combining the strengths of rule-based and learning-based approaches. Evaluation results on the i2b2 Clinical Temporal Relations Challenge corpus show that our approach yields a 17-24% and 8-14% relative reduction in error over a state-of-the-art learning-based baseline system when gold-standard and automatically identified temporal relations are used, respectively.
Publisher: Oxford Journals
ISSN: 1758-0463
Link to Related Resource: http://www.hlt.utdallas.edu/~jld082000/temporal-relations/
Persistent Link: http://dx.doi.org/10.1093/database/bau109
http://hdl.handle.net/10735.1/4277
Terms of Use: CC-BY 4.0 (Attribution)

Files in this item

Files Size Format View
HLTRI-VNg-271629.30.pdf 97.87Mb PDF View/Open Article

This item appears in the following Collection(s)


Show full item record

CC-BY 4.0 (Attribution) Except where otherwise noted, this item's license is described as CC-BY 4.0 (Attribution)