Head Automata and Bilingual Tiling: Translation with Minimal Representations

TL;DR

This paper introduces a novel language model using head automata for efficient dependency parsing and a bilingual tiling approach for machine translation, emphasizing minimal representations and dynamic programming techniques.

Contribution

It proposes a new automata-based model for dependency parsing and a bilingual tiling algorithm for translation, advancing minimal and efficient linguistic representations.

Findings

Automata-based dependency parsing improves efficiency.

Bilingual tiling enhances translation quality.

Cost functions impact model performance.

Abstract

We present a language model consisting of a collection of costed bidirectional finite state automata associated with the head words of phrases. The model is suitable for incremental application of lexical associations in a dynamic programming search for optimal dependency tree derivations. We also present a model and algorithm for machine translation involving optimal ``tiling'' of a dependency tree with entries of a costed bilingual lexicon. Experimental results are reported comparing methods for assigning cost functions to these models. We conclude with a discussion of the adequacy of annotated linguistic strings as representations for machine translation.