Scholarly Data Mining: Making Sense of Scientific Literature

During the last decade the amount of scientific information available on-line increased at an unprecedented rate and this situation is unlikely to change. As a consequence, nowadays researchers are overwhelmed by an enormous and continuously growing number of publications to consider when they perform research activities like the exploration of advances in specific topics, peer reviewing, writing and evaluation of proposals. Natural Language Processing technology plays a key role in enabling intelligent access to the content of scientific publications. By mining the contents of scientific papers, for example, rich scientific knowledge bases can be built, thus supporting more effective information discovery and question answering approaches. Moreover, text summarization technology can help condense long papers to their essential contents so as to speed up the selection of scientific articles of interest or to assist in the manual or automatic generation of state of the art reports. Paraphrase and textual entailment techniques can contribute to the identification of relations across different scientific textual sources, thus, for instance, identifying implicit links between publications. This tutorial provides an overview of approaches to the extraction of knowledge from scientific literature, including the in-depth analysis of the structure of the scientific articles, their semantic interpretation, content extraction, summarization, and visualization.