Knowledge-Rich Temporal Relation Identification and Classification in Clinical Notes
| dc.contributor.author | D'Souza, Jennifer | en_US |
| dc.contributor.author | Ng, Vincent | en_US |
| dc.date.accessioned | 2015-01-21T17:03:59Z | |
| dc.date.available | 2015-01-21T17:03:59Z | |
| dc.date.issued | 2014-10-19 | en_US |
| dc.description.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. | en_US |
| dc.identifier.citation | D'Souza, Jennifer, and Vincent Ng. 2014. "Knowledge-rich temporal relation identification and classification in clinical notes." Database: The Journal of Biological Databases and Curation 2014: 1-20. | en_US |
| dc.identifier.issn | 1758-0463 | en_US |
| dc.identifier.uri | http://hdl.handle.net/10735.1/4277 | |
| dc.identifier.volume | 2014 | en_US |
| dc.publisher | Oxford Journals | en_US |
| dc.relation.uri | http://dx.doi.org/10.1093/database/bau109 | en_US |
| dc.rights | CC-BY 4.0 (Attribution) | en_US |
| dc.rights.holder | ©2014 The Authors | en_US |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/legalcode | en_US |
| dc.source.journal | Database: The Journal of Biological Databases and Curation | en_US |
| dc.subject | Temporal relations | en_US |
| dc.subject | Semantic relations | en_US |
| dc.subject | Classification | en_US |
| dc.subject | Relation types | en_US |
| dc.title | Knowledge-Rich Temporal Relation Identification and Classification in Clinical Notes | en_US |
| dc.type.genre | article | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- HLTRI-VNg-271629.30.pdf
- Size:
- 97.87 MB
- Format:
- Adobe Portable Document Format
- Description:
- Article