Title :
SYNDIKATE-generating text knowledge bases from natural language texts
Author :
Hahn, Udo ; Romacker, Martin
Author_Institution :
Text Knowledge Eng. Lab. Group, Freiburg Univ., Germany
Abstract :
SYNDIKATE is a system for automatically acquiring knowledge from real-world texts and transferring it to formal representation structures which constitute a text knowledge base. We present a system architecture which integrates requirements from the analysis of single sentences, as well as those of referentially linked sentences forming cohesive texts. Properly accounting for text cohesion phenomena is a prerequisite for the completeness and validity of the generated text representation structures, and therefore, also crucial for any information system application making use of automatically generated text knowledge bases in a reliable way, e.g., by inferentially supported fact retrieval
Keywords :
computational linguistics; inference mechanisms; knowledge acquisition; natural languages; text analysis; SYNDIKATE; automatic knowledge acquisition; automatically generated text knowledge bases; cohesive texts; formal representation structures; inferentially supported fact retrieval; information system application; natural language texts; real-world texts; referentially linked sentences; system architecture; text cohesion phenomena; text knowledge base; text knowledge base generation; text representation structures; Assembly systems; Content based retrieval; Content management; Data mining; Filters; Information retrieval; Knowledge acquisition; Knowledge engineering; Management information systems; Natural languages;
Conference_Titel :
Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on
Conference_Location :
Tokyo
Print_ISBN :
0-7803-5731-0
DOI :
10.1109/ICSMC.1999.815676
