Enhancing a biomedical information extraction system with dictionary mining and context disambiguation

Abstract

Journals and conference proceedings represent the dominant mechanisms for reporting new biomedical results. The unstructured nature of such publications makes it difficult to utilize data mining or automated knowledge discovery techniques. Annotation (or markup) of these unstructured documents represents the first step in making these documents machine-analyzable. Often, however, the use of similar (or the same) labels for different entities and the use of different labels for the same entity makes entity extraction difficult in biomedical literature. In this paper we present a system called BioAnnotator for identifying and classifying biological terms in documents. BioAnnotator uses domain-based dictionary lookup for recognizing known terms and a rule engine for discovering new terms. We explain how the system uses a biomedical dictionary to learn extraction patterns for the rule engine and how it disambiguates biological terms that belong to multiple semantic classes.

ProtChew: Automatic Extraction of Protein Names from Biomedical Literature

“…So in the next round we need additional work on i) feature extraction and selection, and ii) incorporating domain knowledge. The approaches presented in [10,12] seems to be complementary to ours and might increase accuracy in future versions of ProtChew.…”

“…Mukherjea et al describe a method that combines manually generated rules with rules learned using UMLS to do biomedical information extraction [12]. Torii and VijayShanker use an unsupervised bootstrapping technique from Word Sense Disambiguation [18].…”

Ontology Support for Biomedical Information Resources

“…Medical World Search Engine [30] uses the UMLS as its built-in knowledge of medical terminology and a selected set of medical resources to perform its searches. BioAnnotator [31] uses domain-based dictionaries (UMLS, LocusLink and GeneAlias) for recognizing known terms within the given text. Due to Figure 7 Top-level ontology of the Nutrients Ontology the incomplete nature of the used dictionaries, a rule engine has been designed for discovering new terms.…”

Thinking PubMed: an Innovative System for Mental Health Domain

“…Medical World Search Engine [12] uses the UMLS as its built-in knowledge of medical terminology and a selected set of medical resources to perform its searches. BioAnnotator [13] uses domain-based dictionaries (UMLS, LocusLink and GeneAlias) for recognizing known terms within the given text. Due to the incomplete nature of the used dictionaries, a rule engine has been designed for discovering new terms.…”