Fast Decoding and Optimal Decoding for Machine Translation

Abstract

A good decoding algorithm is critical to the success of any statistical machine translation system. The decoder's job is to find the translation that is most likely according to set of previously learned parameters (and a formula for combining them). Since the space of possible translations is extremely large, typical decoding algorithms are only able to examine a portion of it, thus risking to miss good solutions. In this paper, we compare the speed and output quality of a traditional stack-based decoding algorithm with two new decoders: a fast greedy decoder and a slow but optimal decoder that treats decoding as an integer-programming optimization problem.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2001
Accession Number
ADA459945

Entities

People

  • Daniel Marcu
  • Kenji Yamada
  • Kevin Knight
  • Michael Jahr
  • Ulrich Germann

Organizations

  • University of Southern California

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Coding
  • Computational Linguistics
  • Computational Science
  • Computer Programming
  • Decoders
  • Decoding
  • Errors
  • Fertility
  • Information Operations
  • Language
  • Linguistics
  • Machine Translation
  • Message Processing
  • Probability
  • Translations

Fields of Study

  • Engineering

Readers

  • Computer Programming and Software Development.
  • Operations Research
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Machine Translation
  • Space