Two Principles and Six Techniques for Rapid Mt Development

In this paper we describe a range of techniques used at NMSU CRL for accelerating the development of MT systems. These techniques enable semi-automatic development of a number of components of a multilingual MT system, thereby enabling rapid deployment of MT capabilities in a new language. First, we describe the core multi-engine, multilingual architecture that enables the different techniques to be rapidly integrated to build an MT system. We show how off-the-shelf components were used in this architecture for fast development. Then we illustrate a set of techniques for semi-automatic acquisition of static resources: (a) automatic induction of grammars, (b) corpus-based acquisition of bilingual glossaries, and automatic acquisition of semantic lexicons through (c) lexical rules and (d) reversal of analysis lexicons to generation lexicons. Finally we describe an automatic testing environment that enables rapid validation of automatically acquired resources. 1 Rapid Development Techniques Static knowledge sources — grammars, lexicons, world knowledge bases — are the most time-consuming concerns in any rule-based machine translation system. It is, therefore, imperative to find ways of speeding up the creation and updating of high-quality, useful static knowledge sources. It is equally imperative to rely on a robust and flexible core computational architecture that allows the concurrent manipulation of a large number of static and dynamic knowledge sources as well as documents and document collections. In this paper, we describe several techniques for facilitating rapid development of MT capabilities for a new language in the framework of an existing multilingual system. Our approach is based on the following two principles: • Heterogeneous, Multi-Engine, Multilingual Architecture: a multi-engine architecture where different subsets of MT techniques can be combined for different languages, accelerates development; it takes longer to perfect any one prespecified MT method for a new language to deliver comparable initial capabilities.