Generation of extended bilingual statistical reports
COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 3
Interactive Multilingual Generation
CICLing '01 Proceedings of the Second International Conference on Computational Linguistics and Intelligent Text Processing
Building applied natural language generation systems
Natural Language Engineering
The NLP role in animated conversation for CALL
ANLC '97 Proceedings of the fifth conference on Applied natural language processing
Multilingual generation and summarization of job adverts: the TREE project
ANLC '97 Proceedings of the fifth conference on Applied natural language processing
A Reference Architecture for Generation Systems
Natural Language Engineering
Evaluating text quality: judging output texts without a clear source
EWNLG '01 Proceedings of the 8th European workshop on Natural Language Generation - Volume 8
A Reference Architecture for Natural Language Generation Systems
Natural Language Engineering
The multilingual generation game: authoring fluent texts in unfamiliar languages
IJCAI'99 Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2
CICLing'03 Proceedings of the 4th international conference on Computational linguistics and intelligent text processing
Hi-index | 0.00 |
The EXCLASS system (Expert Job Evaluation Assistant) is intended to provide intelligent support for job description and classification in the Canadian Public Service. The Job Description Module (JDM) of EXCLASS is used to create conceptual representations of job descriptions, which are used for job evaluation and bilingual generation of textual job descriptions. The design of these representations was subject to two opposing constraints: (1) that they be deep enough to resolve the ambiguities present in textual job descriptions, and (2) that they be close enough to surface linguistic forms that they can be conveniently manipulated by users with little specialized training. The close correspondence of concepts to surface words and phrases, as well as properties of the job description sublanguage, permit a simplified generator design, whereby phrases are prepackaged with a certain amount of linguistic structure, and combined according to a small set of mostly language-independent rules. Text planning, consisting mainly of grouping and ordering of conjoined phrases, is performed manually by the user, and composition of conceptual forms is supported by a "continuous text feedback" function.