Dividing and Conquering Long Sentences in a Translation System

Abstract

The time required for our translation system to handle a sentence of length l is a rapidly growing function of l. We describe here a method for analyzing a sentence into a series of pieces that can be translated sequentially. We show that for sentences with ten or fewer words, it is possible to decrease the translation time by 40% with almost no effect on translation accuracy. We argue that for longer sentences, the effect should be more dramatic.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1992
Accession Number
ADA460274

Entities

People

  • Peter F. Brown
  • Robert L. Mercer
  • Stephen A. Della Pietra
  • Surya Mohanty
  • Vincent J. Della Pietra

Organizations

  • IBM Thomas J. Watson Research Center

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Abstracts
  • Accuracy
  • Algorithms
  • Automated Speech Recognition
  • Computer Vision
  • Decoders
  • Decoding
  • Dynamic Programming
  • English Language
  • Information Operations
  • Language
  • Probability
  • Recognition
  • Training
  • Translations
  • Vocabulary

Readers

  • Library and Information Science
  • Mathematics or Statistics
  • Speech Processing/Speech Recognition.