A hybrid architecture for robust MT using LFG-DOP

Author: Way A.

Source: Journal of Experimental & Theoretical Artificial Intelligence, Volume 11, Number 3, 1 July 1999 , pp. 441-471(31)

Publisher: Taylor and Francis Ltd

Buy & download fulltext article:

Price: $56.94 plus tax (Refund Policy)

Abstract:

We develop a model for machine translation (MT) based on data-oriented parsing (DOP) allied to the syntactic representations of lexical functional grammar (LFG). We begin by showing that in themselves, none of the main paradigmatic approaches to MT currently suffice to the standard required. Nevertheless, each of these approaches contains elements which if properly harnessed should lead to an overall improvement in translation performance. It is in this new hybrid spirit that our search for a better solution to the problems of MT can be seen. We summarize the original DOP model of Bod, as well as the DOT model of translation of Poutsma on which it is based. We demonstrate that DOT is not guaranteed to produce the correct translation, despite provably deriving the most probable translation. We go on to critically evaluate previous attempts at LFG-MT, commenting briefly on particular problem cases for such systems. We then show how the LFG-DOP model of Bod and Kaplan can be extended to serve as a novel hybrid model for MT which promises to improve upon DOT, as well as the pure LFG-based translation model.

Keywords: DATA-ORIENTED; PARSING; LEXICAL; FUNCTIONAL; GRAMMAR; HYBRID; MACHINE; TRANSLATION

Language: English

Document Type: Research article

Publication date: 1999-07-01

More about this publication?