LFG-DOT: Combining Constraint-Based and Empirical Methodologies for Robust MT

The Data-Oriented Parsing Model (DOP, [1]; [2]) has been presented as a promising paradigm for NLP. It has also been used as a basis for Machine Translation (MT) — Data-Oriented TVanslation (DOT, [9]). Lexical Functional Grammar (LFG, [5]) has also been used for MT ([6]). LFG has recently been allied to DOP to produce a new LFG-DOP model ([3]) which improves the robustness of LFG. We summarize the DOT model of translation as well as the DOP model on which it is based. We demonstrate that DOT is not guaranteed to produce the correct translation, despite provably deriving the most probable translation. Finally, we propose a novel hybrid model for MT based on LFG-DOP which promises to improve upon DOT, as well as the pure LFG-based translation model.