Experience with a learning personal assistant
Communications of the ACM
Communications of the ACM
Generalizing automatically generated selectional patterns
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
UMass/Hughes: description of the CIRCUS system used for MUC-5
MUC5 '93 Proceedings of the 5th conference on Message understanding
University of Sheffield: description of the LaSIE system as used for MUC-6
MUC6 '95 Proceedings of the 6th conference on Message understanding
LEAP: a learning apprentice for VLSI design
IJCAI'85 Proceedings of the 9th international joint conference on Artificial intelligence - Volume 1
Automatically generating extraction patterns from untagged text
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
Hi-index | 0.00 |
It is common that a text document contains information that can be interpreted as instructions to pursue a given task. This information called, pattern, can be seen as the triggering mechanism for a set of predefined operations. We are interested in automating the recognition of these patterns for repetitive tasks. We introduce the notion of template generation which allows for the recognition of new patterns that trigger operations. We implemented an algorithm for template generation and we tested it in an electronic publishing application. The tests show that some characteristics of the processed text can be used to adapt the generation process and obtain templates that provide better precision and recall.