Method Mention Extraction from Scientific Research Papers
Hospice Houngbo, Robert E. Mercer · 2012
Scientific publications contain many references to method terminologies used during scientific experiments. New terms are constantly created within the research community, especially in the biomedical domain where thousands of papers are published each week. In this study we report our attempt to automatically extract such method terminologies from scientific research papers, using rule-based and machine learning techniques. We first used some linguistic features to extract fine-grained method sentences from a large biomedical corpus and then applied well established methodologies to extract the method terminologies. We focus the present study on the extraction of method phrases that contain an explicit mention of method keywords such as (algorithm, technique, analysis, approach and method) and other less explicit method terms such as Multiplex Ligation dependent Probe Amplification. Our initial results show an average F-score of 91.89 for the rule-based system and 78.26 for the Conditional Random Field-based machine learning system.