Statistical Machine Translation by Generalized Parsing

Details Statistical Machine Translation by Generalized Parsing Statistical Machine Translation by Generalized Parsing

2004-07-01

arxiv.org/abs/cs/0407005v3

Computer Science

Computation and Language

45 pages, with fixes for generating correct PDF format

Scientific paper

Designers of statistical machine translation (SMT) systems have begun to employ tree-structured translation models. Systems involving tree-structured translation models tend to be complex. This article aims to reduce the conceptual complexity of such systems, in order to make them easier to design, implement, debug, use, study, understand, explain, modify, and improve. In service of this goal, the article extends the theory of semiring parsing to arrive at a novel abstract parsing algorithm with five functional parameters: a logic, a grammar, a semiring, a search strategy, and a termination condition. The article then shows that all the common algorithms that revolve around tree-structured translation models, including hierarchical alignment, inference for parameter estimation, translation, and structured evaluation, can be derived by generalizing two of these parameters -- the grammar and the logic. The article culminates with a recipe for using such generalized parsers to train, apply, and evaluate an SMT system that is driven by tree-structured translation models.

Affiliated with

Also associated with

No associations

Rating

Statistical Machine Translation by Generalized Parsing does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Statistical Machine Translation by Generalized Parsing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Statistical Machine Translation by Generalized Parsing will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-203633