Applying Core Scientific Concepts to Context-Based Citation Recommendation

摘要: The task of recommending relevant scientific literature for a draft academic paper has recently received significant interest. In our effort to ease the discovery and augment writing, we aim improve relevance results based on shallow semantic analysis source document potential documents recommend. We investigate utility automatic argumentative rhetorical annotation this purpose. Specifically, integrate Core Scientific Concepts (CoreSC) classification into prototype context-based citation recommendation system its usefulness task. frame as an information retrieval use categories schemes apply different weights similarity formula. Our show interesting consistent correlations between type sentence containing information.