The Logovista English-Japanese Machine Translation System

TL;DR

This paper details the architecture, development, and real-world evolution of the Logovista English-Japanese rule-based machine translation system, highlighting its practical deployment and ongoing maintenance over two decades.

Contribution

It provides a comprehensive technical and historical account of a large, rule-based MT system developed and maintained commercially from the 1990s to 2012, including its architecture and practical challenges.

Findings

Managed extensive structural ambiguity with chart-based parsing and weighted scoring.

Extended and maintained the system under real-world usage pressures.

Documented the preserved linguistic resources for future research.

Abstract

This paper documents the architecture, development practices, and preserved artifacts of the Logovista English--Japanese machine translation system, a large, explicitly rule-based MT system that was developed and sold commercially from the early 1990s through at least 2012. The system combined hand-authored grammatical rules, a large central dictionary encoding syntactic and semantic constraints, and chart-based parsing with weighted interpretation scoring to manage extensive structural ambiguity. The account emphasizes how the system was extended and maintained under real-world usage pressures, including regression control, ambiguity management, and the limits encountered as coverage expanded. Unlike many rule-based MT systems described primarily in research settings, Logovista was deployed for decades and evolved continuously in response to practical requirements. The paper is intended as a technical and historical record rather than an argument for reviving rule-based MT, and describes the software and linguistic resources that have been preserved for potential future study.