| Summary: | <p>Abstract</p> <p>Background</p> <p>Text-mining can assist biomedical researchers in reducing information overload by extracting useful knowledge from large collections of text. We developed a novel text-mining method based on analyzing the network structure created by symbol co-occurrences as a way to extend the capabilities of knowledge extraction. The method was applied to the task of automatic gene and protein name synonym extraction.</p> <p>Results</p> <p>Performance was measured on a test set consisting of about 50,000 abstracts from one year of MEDLINE. Synonyms retrieved from curated genomics databases were used as a gold standard. The system obtained a maximum F-score of 22.21% (23.18% precision and 21.36% recall), with high efficiency in the use of seed pairs.</p> <p>Conclusion</p> <p>The method performs comparably with other studied methods, does not rely on sophisticated named-entity recognition, and requires little initial seed knowledge.</p>
|
|---|
