Discovering Similarities and Relevance Ranking of Renaissance Composers

• In Event: Studies in Digital and Analog Prosopography: Reconnecting Cultural Networks of the Early Modern Era

Abstract

Natural Language Processing (NLP) plays a key role in the systematic analysis of a large amount of textual sources. A first step towards the application of machine understanding to musicological knowledge is the automatic annotation of texts. Once documents are properly annotated, complex structures and meaningful relations between pieces of information may emerge. In this prosopographic study, we apply Entity Linking, a well known NLP technique, to a large corpus of artist biographies. Based on this technique, which acts as a bridge between plain text and knowledge inventory, we can create a graph of musical entities. Applying the method to a large corpus of online biographies, we are then able to identify similarities between Renaissance composers, based on common aspects found in the biographies. Finally, artists are ranked according to a relevance measure, which is computed in a similar way to the way web pages are ranked by a search engine.

Author

• Sergio Oramas, Pompeu Fabra University