• Publications
  • Influence
Adaptive Information Extraction from Text by Rule Induction and Generalisation
TLDR
The role of shallow NLP in rule induction is discussed, and the algorithm has a considerable success story and real world applications have been developed and licenses have been released to external companies for building other applications.
A Comparative Evaluation of Term Recognition Algorithms
TLDR
This paper evaluated the six approaches using two different corpora and showed how the voting algorithm performs best on one corpus and less well using the Genia corpus, indicating that choice and design of corpus has a major impact on the evaluation of term recognition algorithms.
S-CREAM - Semi-automatic CREAtion of Metadata
TLDR
OntoMat-Annotizer extract with the help of Amilcare knowledge structure from web pages through the use of knowledge extraction rules, the result of a learning-cycle based on already annotated pages.
MnM: Ontology Driven Semi-automatic and Automatic Support for Semantic Markup
TLDR
M is presented, an annotation tool which provides both automated and semi-automated support for annotating web pages with semantic contents and integrates a web browser with an ontology editor and provides open APIs to link to ontology servers and for integrating information extraction tools.
Recent advances in methods of lexical semantic relatedness – a survey
TLDR
A review of the literature with a focus on recent methods that are not covered in previous surveys, and an evaluation of lexical semantic relatedness methods and a discussion of useful lessons for the development and application of such methods.
Learning to Harvest Information for the Semantic Web
TLDR
A methodology for harvesting information from large distributed repositories (e.g. large Web sites) with minimum user intervention is described and its implementation in the Armadillo system is described.
(LP) 2 , an Adaptive Algorithm for Information Extraction from Web-related Texts
TLDR
This paper focuses on the NLP-based generalisation and the strategy for pruning both the search space and the final rule set, and shows a significant gain in using NLP in terms of effectiveness and reduction of training time.
Hybrid Search: Effectively Combining Keywords and Semantic Searches
TLDR
This paper defines hybrid search formally, discusses its compatibility with the current semantic trends and presents a reference implementation: K-Search, a search method supporting both document and knowledge retrieval via the flexible combination of ontology-based search and keyword-based matching.
...
1
2
3
4
5
...