Computer generation of multiparagraph English text
Computational Linguistics
Computational Linguistics
Enhancing explanation coherence with rhetorical strategies
EACL '89 Proceedings of the fourth conference on European chapter of the Association for Computational Linguistics
Salience: the key to the selection problem in natural language generation
ACL '82 Proceedings of the 20th annual meeting on Association for Computational Linguistics
ACL '81 Proceedings of the 19th annual meeting on Association for Computational Linguistics
On verbosity levels in cognitive problem solvers
COLING '82 Proceedings of the 9th conference on Computational linguistics - Volume 2
Explaining and justifying expert consulting programs
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Causal understanding of patient illness in medical diagnosis
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
A precedence scheme for selection and explanation of therapies
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Tailoring explanations for the user
IJCAI'85 Proceedings of the 9th international joint conference on Artificial intelligence - Volume 2
Empirical and model-based reasoning in expert systems
IJCAI'85 Proceedings of the 9th international joint conference on Artificial intelligence - Volume 1
| Hi-index | 0.00 |
Traditional methods for explaining programs provide explanations by converting to English the code of the program or traces of the execution of that code. While such methods can provide adequate explanations of what the program does or did, they typically cannot provide justifications of the code without resorting to canned-text explanations. That is, such systems cannot tell why what the system is doing is a reasonable thing to be doing. The problem is that the knowledge required to provide these justifications is needed only when the program is being written and does not appear in the code itself. In the XPLAIN system, an automatic programming approach is used to capture some of the knowledge necessary to provide these justifications. The XPLAIN system uses an automatic programmer to generate the consulting program by refinement from abstract goals. The automatic programmer uses a domain model, consisting of facts about the application domain, and a set of domain principles which drive the refinement process forward. By keeping around a trace of the execution of the automatic programmer it is possible to provide justifications of the code using techniques similar to the traditional methods outlined above. This paper discusses the system described above and outlines additional advantages this approach has for explanation.