Abstract
We present a small set of attachment heuristics for postnominal PPs occurring in full-text articles related to enzymes. A detailed analysis of the results suggests their utility for extraction of relations expressed by nominalizations (often with several attached PPs). The system achieves 82% accuracy on a manually annotated test corpus of over 3000 PPs from varied biomedical texts.
Cite
CITATION STYLE
Schuman, J., & Bergler, S. (2006). Postnominal prepositional phrase attachment in proteomics. In HLT-NAACL 2006 - BioNLP 2006: Linking Natural Language Processing and Biology: Towards Deeper Biological Literature Analysis, Proceedings of the Workshop (pp. 82–89). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1654415.1654432
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
