Designing Adaptive Information Extraction for the Semantic Web in Amilcare

Ciravegna, Professor Fabio and Wilks, Professor Yorick (2003) Designing Adaptive Information Extraction for the Semantic Web in Amilcare, in Handschuh, Siegfried and Staab, dr Steffen, Eds. Annotation for the Semantic Web. IOS Press.

Full text available as:

PDF - Requires Adobe Acrobat Reader or other PDF viewer.

A crucial aspect of creating the Semantic Web (SW) is to enable users to create machinereadableWeb content. Emphasis in the research community has till now been put on building tools for manual annotation of documents (e.g. [18]), but only recently has the problem of producing automatic or semi-automatic methods for annotating documents become an issue [17, 27]. The main problem with manual annotation is that it is a difficult, slow, time-consuming and tedious process that involves high costs and very often a large number of errors as well (up to 25% in some cases [24]). The latter is especially true in case of user with no experience of document annotation (naive annotators), while it slightly improves with expert annotators (about 15%). Manual annotation of documents by naive Web users is quite unlikely to be correct or even performed at all. Information Extraction from texts (IE) is an automatic method for locating important facts in electronic documents for successive use, e.g. for document annotation or for information storing (such as populating an ontology with instances). IE can provide support in document annotation either in an automatic way (unsupervised extraction of information) or semi-automatic way (e.g. as support for human annotators in locating relevant facts in documents, via information highlighting). In this paper we present Amilcare, an adaptive IE system designed as support to document annotation in the SW framework. Amilcare is currently used at a number of sites and has been integrated in a number of SW annotation systems.

Contact the site administrator at: hg@ecs.soton.ac.uk