Melita: Active Document Enrichment using Adaptive Information Extraction from Text
(2002) Melita: Active Document Enrichment using Adaptive Information Extraction from Text. In Proceedings 1st International Semantic Web Conference, (ISWC2002), Sardinia, Italia.
Full text available as:
 | PDF - Requires Adobe Acrobat Reader or other PDF viewer. |
The traditional process of document annotation for knowledge identification and extraction in the Semantic Web (SW) is complex and time consuming, as it requires human manual annotation. There is currently a strong interest in Text Mining technologies (and in particular in Human Language-based Technologies), for reducing the burden of text annotation e.g. for Knowledge Management [Maybury2001]. In this poster we present Melita, an annotation interface that uses Adaptive Information Extraction from texts (IE) for reducing the burden of text annotation. In Melita, adaptation starts with the definition of a scenario, including a tag set for annotation (possibly organized as an ontology) and a corpus of texts to be annotated. Annotations are inserted by first selecting a tag from the ontology and then identifying the text area to annotate with the mouse. Differently from similar annotation tools [Day1997, Cunningham2001], Melita actively supports corpus annotation using Amilcare, an adaptive Information Extraction (IE) tool based on the (LP)2 algorithm [Ciravegna2001].
| Keywords: | knowledge acquisition, corpus annotation, user-interfaces, adaptive information extraction |
|---|---|
| Subjects: | AKT Challenges > Knowledge acquisition |
| ID Code: | 116 |
| Deposited By: | Brewster, Christopher |
| Deposited On: | 27 February 2003 |
| Alternative Locations: | http://www.dcs.shef.ac.uk/~fabio/cira-papers.html |
Contact the site administrator at: hg@ecs.soton.ac.uk