Speaker
Summary
With an overwhelming amount of publications, it is not surprising that there is so much interest in techniques which can identify, extract, manage, integrate and exploit the knowledge in them. Numerous large-scale repositories storing a huge amount of papers in electronic form are available to the researcher. But in order to unleash the knowledge hidden in these repositories, we need techniques which go beyond the traditional meaning of metadata: we need to analyze the content of the papers stored in the repositories using text mining techniques. These techniques are data driven and provide automatically semantic metadata which allow us to perform semantic searching. The National Centre for Text Mining is using techniques based on natural language processing to analyze not only abstracts but also full texts, such as term identification, semantic tagging, automatic summarization, fact extraction, disambiguation, association mining. These techniques enrich the vast literature with meaning and in turn allow the development of customized and personalized systems for scholarly communication.
View Sophia Ananiadou's profile
