Knowledge-based Extraction of Cause–Effect Relations from Biomedical Text

We propose a knowledge-based approach for extraction of Cause–Effect (CE) relations from biomedical text. Our is combination an unsupervised machine learning technique to discover causal triggers and set high-precision linguistic rules identify cause/effect arguments these triggers. evaluate our using corpus 58,761 Leukaemia-related PubMed abstracts consisting 568,528 sentences. could extract 152,655 CE triplets this where each triplet consists cause phrase, effect trigger. As compared the existing knowledge base—SemMedDB [5]—the number extractions are almost twice. Moreover, proposed outperformed SemRep [7] on dataset 500