Duplicate Literature Detection for Cross-Library Search

The proliferation of online digital libraries offers users a great opportunity to search their desired literatures on Web. Cross-library search applications can help users search more literature information from multiple digital libraries. Duplicate literatures detection is always a necessary step when merging the search results from multiple digital libraries due to heterogeneity and autonomy of digital libraries. To this end, this paper proposes a holistic solution which includes achieving automatic training set, holistic attribute mapping, and weight of attribute training. The experiments on real digital libraries show that the proposed solution is highly effective.