OpenLogos machine translation: philosophy, model, resources and customization

Abstract

This paper reviews the OpenLogos rule-based machine translation system, and describes its model architecture as an incremental pipeline process. The paper also describes OpenLogos resources and their customization to specific application domains. One of the key aspects of rule-based machine translation systems intelligence is the symbology employed by these systems in representing natural language internally. The paper offers details about the OpenLogos semantico-syntactic abstract representation language known as SAL. The paper also shows how OpenLogos has addressed classic problems of rule-based machine translation, such as the cognitive complexity and ambiguity encountered in natural language processing, illustrating how SAL helps overcome them in ways distinct from other existing rule-based machine translation systems. The paper illustrates how the intelligence inherent in SAL contributes to translation quality, presenting examples of OpenLogos output of a kind that non-linguistic systems would likely have difficulty emulating. The paper shows the unique manner in which OpenLogos applies the rulebase to the input stream and the kind of results produced that are characteristic of the OpenLogos output. Finally, the paper deals with an important advantage of rule-based machine translation systems, A. Barreiro (B) CLUP,

Deep open-source machine translation

“…However, the majority of these systems are of a proprietary nature; when the project concludes, the resources that were developed are rarely made available to other researchers, so it is difficult for the field to directly benefit from what was learned throughout the course of development. A notable exception to this is the OpenLogos System (Barreiro et al 2011), who have opened up their system for collaborative development.…”

Sustainable language technology for African languages

“…This is selected if no rule selects another interpretation. The structure of SALAMA resembles the processing method of OpenLogos (Scott and Barreiro 2009;Barreiro et al 2011) including modular pipeline structure.…”

Paraphrasing of Italian Support Verb Constructions based on Lexical and Grammatical Resources

“…The system was created by Scott in 1970 but then has been extended by the German Research Centre for Artificial Intelligence (DFKI). It is an old rule-based system MT, but its resources, such as the electronic dictionary, the rules and the SAL which is embedded in the dictionaries, are valuable (Barreiro et al, 2011).…”