TurkuNLP Entry for Interactive Bio-ID Assignment




Suwisa Kaewphan, Farrokh Mehryary, Kai Hakala, Tapio Salakoski, Filip Ginter

Cecilia Arighi, Qinghua Wang, Cathy Wu

BioCreative

2018

Proceedings of the BioCreative VI Workshop

32

35

978-84-948397-0-2

http://www.biocreative.org/resources/publications/bcvi-proceedings/

https://research.utu.fi/converis/portal/detail/Publication/28249832



We participate in BioCreative VI: Interactive Bio-ID Assignment (Bio-ID) track by developing systems capable of named entity recognition and normalization of 6 entity types, namely Protein, Cell, Organism, Tissue, Molecule and Cellular. Our named entity recognition system is based on conditional random fields. For named entity normalization, we apply fuzzy matching and rule-based system to disambiguate and assign unique identifiers to the entities. The official evaluation shows that average F1-scores of all entity types for our recognition and normalization systems on strict span offsets are 0.720 and 0.668, respectively.


Last updated on 2024-26-11 at 22:56