Preprint Open Access
Semantic metadata annotation: tagging medline abstracts for enhanced information access
Ibekwe, Fidelia
The object of this study is to develop methods for automatically annotating the argumentative role of sentences in scientific abstracts. Working from Medline abstracts, we classified sentences into four major argumentative roles: objective, method, result, conclusion. The idea is that if the role of each sentence can be marked up, then this metadata can be used during information retrieval to seek for particular types of information such as novelty, conclusions, methodologies, aims/goals of a scientific piece of work.
Files
(204.7 kB)
| Name | Size | |
|---|---|---|
|
2009-06-23-paper-ISKOUK-Conference-FIbekwe.pdf
md5:a455ff3df6552409bbfa5f9020294e25 |
204.7 kB | Download |
42
24
views
downloads
| All versions | This version | |
|---|---|---|
| Views | 42 | 42 |
| Downloads | 24 | 24 |
| Data volume | 4.9 MB | 4.9 MB |
| Unique views | 27 | 27 |
| Unique downloads | 23 | 23 |
Indexed in
- Publication date:
- June 23, 2009
- DOI:
-
- Keyword(s):
- semantic metadata annotation discourse analysis biomedical abstracts argumentative role sentence classification
- Subject(s):
- Meeting:
- ISKO UK Conference 2009 - Content Architecture: Exploiting and Managing Diverse Resources (ISKOUK:2009), London, UK, 22-23 June 2009 (Session 6A)
- Related identifiers:
- Supplementary material
- 10.5281/zenodo.7093144 (Presentation)
- 10.5281/zenodo.7093179 (Video/Audio)
- Communities:
- License (for files):
- Creative Commons Non-Commercial (Any)