The Penman Language Generation Project
نویسندگان
چکیده
The natural language sentence generation program Penman provides computational technology for generating English sentences and paragraphs, starting with input specifications of a non-linguistic kind. The research goals underlying Penman are threefold: to provide a useful and theoretically motivated resource for other research and development groups and the computational community at large, to provide a framework in which to conduct investigations into the nature of language, and eventually to provide a text generation system that can be used routinely by system developers. Penman is being used by computer scientists (as the output medium of their programs, among others projects in human-compu te r communication, expert system explanation, and interface design) and by linguists (as a reference and research tool).
منابع مشابه
The Current Status of the Penman Language Generation System
In addition, the project has entered into two collaborations that show great promise. The KOMET project at the IPSI Insti tute in West Germany (funded by the German Federal Government) is a new project with goals very similar to our own. In addition to funding some of our work, they are building a systemic grammar of German and are collaborating on our parsing research. The Department of Lingui...
متن کاملThe Penman Natural Language Project Systemics-Based Machine Translation
The development of an integrated knowledgebased machine-aided translation system based on Systemic Linguistics. Parts of the system are to function as modules to be incorporated in the MAT system being codeveloped with CMU and CRL. Our work involves the enhancement of Penman's existing parsing technology to match the level of the language generation system; the development of ancillary knowledg...
متن کاملMerging the English and the German Upper Model
A detailed comparison of the Penman Upper Model and the KOMET German Upper Model is carried out in order to construct a new Merged Upper Model capable of serving as the ideational basis for automatic text generation in both English and German. Previously proposed criteria for conducting such a merge are expanded on and evaluated. It is established that no (semi-)automatic merging of such knowle...
متن کاملComputational and Quantitative Studies
Michael Halliday is a linguist whose ideas have inspired computational linguists over a prolonged period. His earliest research work took place in China and with Chinese languages. In the late 1950s, as an assistant lecturer in Chinese at Cambridge, he worked in a project concerned with machine translation at the Cambridge Language Research Unit (directed by Margaret Masterman and which was lat...
متن کاملMultilingual Natural Language Generation (Experience from AGILE Project)1
Multilingual Natural Language Generation is an interesting and challenging field of Natural Language Processing. Automatic generation of texts in natural language could be viewed as a final part of automated translation process from one language to another. Alternative approach is given the chance with development of modern Natural Language Processing technologies, which concentrate the researc...
متن کامل