Syntax and Machine Translation
The Metal Project
Unlike much theoretical linguistics, both the comparative perspective and the automatic aspect of Machine Translation reveal that there cannot be a clear-cut borderline between grammar and lexicon. The interdependence of grammatical computation and lexical storage has become extremely obvious during the research and development work in the METAL-project. After outlining the history of this project, section 1 of this paper sketches the system's projected application environment. The systern's main lexical tools are discussed in section 2, and section 3 deals with its main grammatical techniques. The final section raises a number of problems and issues for further research. Some of these are well-known but still await a satisfactory solution given the present (1987) state of the project. Others are raised much less often and derive from the technical nature of the texts that METAL is intended to translate.
Cited by (1)
Cited by one other publication
Casas, Noe, Marta R. Costa-jussà, José A. R. Fonollosa, Juan A. Alonso & Ramón Fanlo
2021.
Linguistic knowledge-based vocabularies for Neural Machine Translation.
Natural Language Engineering 27:4
► pp. 485 ff.
This list is based on CrossRef data as of 5 july 2024. Please note that it may not be complete. Sources presented here have been supplied by the respective publishers.
Any errors therein should be reported to them.