Improved Phrase Translation Modeling Using Maximum A-Posteriori (MAP) Adaptation

Abstract

In this paper, we explore several methods of improving the estimation of translation model probabilities for phrase-based statistical machine translation given in-domain data sparsity. We introduce a hierarchical variant of MAP adaptation for domain adaptation with an arbitrary number of out-of-domain models. We compare this adaptation technique to linear interpolation and phrase table fill-up. Additionally, we note that domain adaptation can have a smoothing effect, and we explore the interaction between smoothing and the incorporation of out-of-domain data. We find that the relative contributions of smoothing and interpolation depend on the datasets used. For both the IWSLT 2011 and WMT 2011 English-French datasets, the MAP adaptation method we present improves on a baseline system by 1.5+ BLEU points.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2013
Accession Number
ADA604450

Entities

People

  • A. R. Aminzadeh
  • Jennifer Drexler
  • Timothy Anderson
  • Wade Shen

Organizations

  • Air Force Research Laboratory

Tags

Communities of Interest

  • C4I

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Computational Science
  • Department Of Defense
  • Government Procurement
  • Governments
  • Hierarchies
  • Interpolation
  • Language
  • Machine Translation
  • Military Research
  • Motor Skills
  • Probability
  • Standards
  • Translations
  • United States
  • United States Government

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Computational Linguistics
  • Distributed Systems and Data Platform Development

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Translation