Self-Organizing Machine Translation: Example-Driven Induction of Transfer Functions

TL;DR

This paper introduces a novel example-driven machine translation system that infers transfer functions from bilingual data using a new formalism, combining psycholinguistic principles with optimization techniques, demonstrating promising results in multiple language pairs.

Contribution

It presents a new formalism called marker-normal form and a system called METLA-1 that merges psycholinguistic insights with data-driven transfer function induction for machine translation.

Findings

METLA-1 successfully infers transfer functions for English-French and English-Urdu.

The system's results are linguistically and psychologically grounded.

METLA-1 performs competitively against Hidden Markov Model-based prototypes.

Abstract

With the advent of faster computers, the notion of doing machine translation from a huge stored database of translation examples is no longer unreasonable. This paper describes an attempt to merge the Example-Based Machine Translation (EBMT) approach with psycholinguistic principles. A new formalism for context- free grammars, called *marker-normal form*, is demonstrated and used to describe language data in a way compatible with psycholinguistic theories. By embedding this formalism in a standard multivariate optimization framework, a system can be built that infers correct transfer functions for a set of bilingual sentence pairs and then uses those functions to translate novel sentences. The validity of this line of reasoning has been tested in the development of a system called METLA-1. This system has been used to infer English->French and English->Urdu transfer functions from small corpora. The results of those experiments are examined, both in engineering terms as well as in more linguistic terms. In general, the results of these experiments were psycho- logically and linguistically well-grounded while still achieving a respectable level of success when compared against a similar prototype using Hidden Markov Models.