Improved acronym disambiguation - release of updated software service and paper
2010-04-01
The ultimate goal of abbreviation management is to disambiguate every occurrence of an abbreviation into its expanded form (concept or sense).
To collect expanded forms for abbreviations, previous studies have recognized abbreviations and their expanded forms in parenthetical expressions of bio-medical texts. However, expanded forms extracted by abbreviation recognition are mixtures of concepts/senses and their term variations. A sense inventory, in which expanded forms are clustered into senses, constitutes a key resource to provide possible concepts or senses for abbreviation disambiguation.
The sense inventory is available at http://www.nactem.ac.uk/software/acromine/ and the acronym disamiguator is available at http://www.nactem.ac.uk/software/acromine_disambiguation/
The paper presents a machine learning approach to the automatic clustering of terms, and evaluates the performance of the resulting sense inventory in an experiment of acronym disambiguation.
Okazaki, N., Ananiadou, S., Tsujii, J. (2010) Building a High Quality Sense Inventory for Improved Abbreviation Disambiguation. Bioinformatics, Oxford University Press.
Previous item | Next item |
Back to news summary page |
Featured News
- Invited talk at BioASQ 2023
- Prof. Ananiadou appointed as Senior Area Chair for ACL 2023 and IJCNLP-AACL 2023
- New Knowledge Transfer Partnership with 10BE5
- Panellist at Digital Trust and Society Forum 2023
- Chinese Government AwardAward for PhD student Tianlin Zhang
- Advances in Data Science and AI Conference 2023
- Keynote talk at EMBL-EBI industry club Machine Learning for Text Mining
- Talk at Open Data Science Conference (ODSC)
- BioLaySumm 2023 - Shared Task @ BioNLP 2023
- Prof. Ananiadou gives talk as distinguished speaker in the Women in AI speaker series
- Junichi Tsujii awarded Order of the Sacred Treasure, Gold Rays with Neck Ribbon
Other News & Events
- Keynote Talk at the Festival of AI
- Recent funding successes for Prof. Sophia Ananiadou
- New article on using neural architectures to aggregate sequence labels from multiple annnotators
- New article on improving biomedical extractive summarisation using domain knowledge
- New article on automated detection and analysis of depression and stress in social media data