Accuracy-Based Scoring for DOT: Towards Direct Error Minimization for Data-Oriented Translation

In this work we present a novel technique to rescore fragments in the Data-Oriented Translation model based on their contribution to translation accuracy. We describe three new rescoring methods, and present the initial results of a pilot experiment on a small subset of the Europarl corpus. This work is a proof-of-concept, and is the first step in directly optimizing translation decisions solely on the hypothesized accuracy of potential translations resulting from those decisions.

• Type: Journal
• Year: 2009
• Where: EMNLP
• Authors: Daniel Galron, Sergio Penkale, Andy Way, I. Dan Melamed
• Keywords: Data-Oriented Translation Model, EMNLP 2009, Natural Language Processing, Translation Accuracy, Translation Decisions