Automated Semantic Analysis of Schematic Data: Learning-based Techniques for Scalable and Automated Semantic Understanding of Template Generated Schematic Web Content

Content in numerous data sourcesare not directly amenable to machine processing. This book describes techniques for automated semantic analysis ofschematic content which are characterized by being populated from backend databases. Starting with a seed set of hand-labeled instances of semanticconcepts in a set of HTML documents, a technique is devised thatbootstraps an annotation process for automatic identification ofconcept instances present in other documents. The technique exploitsthe observation that semantically related items in schematic HTMLdocuments exhibit consistency in presentation style and spatiallocality to learn statistical concept models, using light-weightsemantic features. This model directs the annotation of diverse Web documents possessing similar content semantics. The power of these techniques is demonstrated through applications developed for real-life problems that includeaudio-based assistive browsing for non-visual Web access, focused browsing on handhelds with semantic bookmarks, text data cleaning, and accurate identification of remote homologs of biological protein sequences.