conference · 2004
Towards Automatic Learning of a Structure Ontology For Technical Articles
See where this sits in the topic map →Summary AI-generated
- TL;DR
- While keyword-based search is often successful, many information retrieval tasks require an understanding of data semantics.
- Problem
- Not specified in the abstract.
- Method
- The authors propose an approach that combines a hand-crafted ontology with a robust inductive inference method to assign semantic labels to sections of technical articles on the Web.
- Results
- Preliminary results evaluate the precision of the assigned semantic labels and the accuracy of responses to semantic queries.
- Contributions
- Not specified in the abstract.
- Limitations
- Not specified in the abstract.
- Takeaways
- Combined with a custom query language, this approach supports complex queries that current tools cannot resolve.
- Applications
- Not specified in the abstract.
- Topics
- Automatic learning, structure ontologies, technical articles, semantic information retrieval
- For industry
- Not specified in the abstract.
- Why it matters
- Not specified in the abstract.
Abstract
Despite the high level of success attained by keyword based information retrieval methods, a significant fraction of information retrieval tasks still needs to take into account the semantics of the data. We propose a method that combines an hand-crafted ontology with a robust inductive inference method to assign semantic labels to pieces of technical articles available on the Web. This approach, together with a query language developed for the purpose, supports queries that cannot be resolved using currently available tools. We present preliminary results that describe the precision of the assigned labels and the accuracy of the replies to the semantic queries present to the system.