A survey of knowledge acquisition techniques and tools
Knowledge Acquisition
Knowledge elicitation techniques for knowledge-based systems
Knowledge elicitation: principle, techniques and applications
Varieties of knowledge elicitation techniques
International Journal of Human-Computer Studies
Automated knowledge acquisition for instructional text generation
Proceedings of the 20th annual international conference on Computer documentation
Patent claim processing for readability: structure analysis and term explanation
PATENT '03 Proceedings of the ACL-2003 workshop on Patent corpus processing - Volume 20
Towards designing natural language interfaces
CICLing'03 Proceedings of the 4th international conference on Computational linguistics and intelligent text processing
| Hi-index | 4.10 |
To safeguard an invention, the inventor must apply for a patent. The first step is to author a patent claim. The claim is the focal point of a patent disclosure and the actual subject of legal protection. Claims contain crucial information about the invention and must be formulated according to precise syntactic, lexical, and stylistic rules, as specified in the guidelines pioneered by the German Patent Office and commonly accepted in the US and other countries. To successfully author a patent claim, you need two distinct types of expert knowledge: knowledge about the sublanguage of patents as legal documents and knowledge about the invention's technology. This is why inventors (who possess the technical knowledge) need the services of lawyers or patent experts (who possess the legal knowledge) to author a claim. To automate and thereby simplify the process of patent authoring, a system must elicit both kinds of knowledge. Legal knowledge essentially manifests itself in the constraints on and preferences concerning the lexical and grammatical language elements in a patent disclosure. This type of knowledge applies to all patents regardless of domain and need not be elicited more than once. Technical knowledge and the language of its description are much more varied; thus, its elicitation should be conducted separately for each patent document. Authoring patent disclosures is a complex task well suited for human-computer interaction, and patent claim composition is the most difficult part. Even for experts, claim analysis and synthesis is time-consuming. In hopes of alleviating this situation, we developed an experimental system for semiautomatic authoring of patent claims. The first implementation of our workstation, designed for both inventors and patent experts, is devoted to patent claim composition. This article focuses on interactively eliciting technical knowledge from inventors. These techniques let us readily acquire knowledge about different domains. When they are coupled with text generation, we can ultimately simplify text composition tasks faced by all sorts of professionals.