Protein-protein interaction extraction method using shallow parsing
作融合浅层句法分析的蛋白质互作用信息抽取方法*

Abstract: In order to solve problems of protein-protein interaction extraction based on traditional machine learning methods, an information extraction method using shallow parsing was proposed. This method first processed candidate sentences by shallow parsing including phrase chunking, appositive parsing, coordinative parsing and sentence splitting. After this step, sentences were divided into multiple individual grammar units. Secondly, protein-protein interactions were extracted from each unit using maximum entropy classification method. Tested in the BC-PPI corpus, this method achieved F1 value of 62.1%. Comparative experiments show the method decreases false positives and false negatives efficiently and improves performances of information extraction.