Text Mining Workflows for Indexing Archives with Automatically Extracted Semantic Metadata

RIZA BATISTA-NAVARRO; AXEL J. SOTO; WILLIAM ULATE; SOPHIA ANANIADOU

Hannover

Conferencia; 20th International Conference on Theory and Practice of Digital Libraries, TPDL 2016; 2016

TPDL

With the vast amounts of textual data that many digitallibraries hold, finding information relevant to users has become a challenge.The unstructured and ambiguous nature of natural language inwhich documents are written, poses a barrier to the accessibility and discoveryof information. This can be alleviated by indexing documents withsemantic metadata, e.g., by tagging them with terms that could indicatetheir ?aboutness?. As manually indexing these documents is impracticable,automatic tools capable of generating semantic metadata andbuilding search indexes have become attractive solutions. In this tutorial,we demonstrate how digital library developers and managers can usethe Argo text mining platform to develop their own customised, modularworkflows for automatic semantic metadata generation and searchindex construction. In this way, we are providing digital library practitionerswith the necessary technical know-how on building semanticsearch indexes without any programming effort, owing to Argo?s graphicalinterface for workflow construction and execution. We believe thatthis in turn will allow various digital libraries to build search systemsthat will enable their users to find and discover information of interestmore efficiently and accurately