Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
Information extraction as a basis for portable text classification systems
Information extraction as a basis for portable text classification systems
Silk from a sow's ear: extracting usable structures from the Web
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Agents for information gathering
Software agents
Wrapper generation for semi-structured Internet sources
ACM SIGMOD Record
Ontology-based extraction and structuring of information from data-rich unstructured documents
Proceedings of the seventh international conference on Information and knowledge management
Java Examples in a Nutshell
Modern Information Retrieval
IEEE Internet Computing
In the quest of the missing link
IJCAI'97 Proceedings of the 15th international joint conference on Artifical intelligence - Volume 1
| Hi-index | 0.00 |
In the Web, there are classes of pages with similar structuring and contents (e.g., call for papers pages, references, etc), which are interrelated forming clusters (e.g., Science). We propose an architecture of cognitive multiagent systems for information retrieval and extraction from these clusters. Each agent processes one class employing reusable ontologies to recognize pages, extract all possible useful information and communicate with the others agents. Whenever it identifies information interesting to another agent, it forwards this information to that agent. These "hot hints" usually contain much less garbage than search engine results do. The agent architecture presents many sorts of reuse: all the code, DB definitions, knowledge and services of the search engines. We got promising results using Java and Jess.