Juho Heimonen

References

(Heimonen et al., 2010) ⇒ Juho Heimonen, Jari Bj¨orne, and Tapio Salakoski. (2010). “Reconstruction of Semantic Relationships from Their Projections in Biomolecular Domain.” In: Proceedings of the 2010 Workshop on Biomedical Natural Language Processing.
- ABSTRACT: The extraction of nested, semantically rich relationships of biological entities has recently gained popularity in the biomedical text mining community. To move toward this objective, a method is proposed for reconstructing original semantic relationship graphs from projections, where each node and edge is mapped to the representative of its equivalence class, by determining the relationship argument combinations that represent real relationships. It generalises the limited postprocessing step of the method of Bj¨orne et al. (2010) and hence extends this extraction method to arbitrarily deep relationships with unrestricted primary argument combinations. The viability of the method is shown by successfully extracting nested relationships in BioInfer and the corpus of the BioNLP’09 Shared Task on Event Extraction. The reported results, to the best of our knowledge, are the first for the nested relationships in BioInfer on a task in which only named entities are given.

(Heimonen et al., 2008) ⇒ Juho Heimonen, Sampo Pyysalo, Filip Ginter, and Tapio Salakoski. (2008). “Complex-to-Pairwise Mapping of Biological Relationships Using a Semantic Network Representation.” In: Proceedings of the Third International Symposium on Semantic Mining in Biomedicine (SMBM 2008).
- ABSTRACT: This study examines representations of proteinâprotein interactions focusing on the mapping between simple, pairwise annotation and complex, structured annotation. A simple semantic network representation equivalent to the BioInfer predicate formalism is introduced and used to transform the complex annotation of BioInfer into pairwise annotation through hand-written rules. Evaluation shows that this binarisation can be largely validly performed with limited loss of information, but also reveals specific challenges. The binarised BioInfer is the first corpus of this type where the inclusion rules are formalised to the level of a computational implementation and is freely available at http://www.it.utu.fi/BioInfer.

(Pyysalo et al., 2007) ⇒ Sampo Pyysalo, Filip Ginter, Juho Heimonen, Jari Bj¨orne, Jorma Boberg, Jouni J¨arvinen, and Tapio Salakoski. (2007). “BioInfer: A corpus for information extraction in the biomedical domain.” In: BMC Bioinformatics, 8(1).