Estimating Grammar Correctness for a Priori Estimation of Machine Translation Post-Editing Effort

We present a supervised learning pilot application for estimating Machine Translation (MT) output reusability, in view of supporting a human post-editor of MT content. We train our model on typed dependencies (labeled grammar relationships) extracted from human reference and raw MT data, to then predict grammar relationship correctness values that we aggregate to provide a binary segmentlevel evaluation. In view of scaling up to larger data, we provide implemented

• Publication year

  2014

• Venue

  HaCaT@EACL

• Publication date

  2014-04-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.3115/v1/W14-0303
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Linguistic Features for Quality Estimation

  2012cited by this paper
• Combining Modifications to Multinomial Naive Bayes for Text Classification

  2012cited by this paper
• Exploiting Objective Annotations for Minimising Translation Post-editing Effort

  2011cited by this paper
• Improving Machine Translation Quality Prediction with Syntactic Tree Kernels

  2011cited by this paper
• Large-Scale Machine Learning with Stochastic Gradient Descent

  2010cited by this paper
• The WEKA data mining software: an update

  2009cited by this paper
• Learning Labelled Dependencies in Machine Translation Evaluation

  2009cited by this paper
• The Stanford Typed Dependencies Representation

  2008cited by this paper
• Moses: Open Source Toolkit for Statistical Machine Translation

  2007cited by this paper
• Dependency-Based Automatic Evaluation for Machine Translation

  2007cited by this paper
• Statistical Phrase-Based Post-Editing

  2007cited by this paper
• A New Conjugate Gradient Method with Guaranteed Descent and an Efficient Line Search

  2005cited by this paper
• Europarl: A Parallel Corpus for Statistical Machine Translation

  2005cited by this paper
• Syntactic Features for Evaluation of Machine Translation

  2005cited by this paper
• Sentence-level MT evaluation without reference translations: beyond language modeling

  2005cited by this paper
• Solving large scale linear prediction problems using stochastic gradient descent algorithms

  2004cited by this paper
• Are Loss Functions All the Same?

  2004cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper
• On the Learnability and Design of Output Codes for Multiclass Problems

  2002influential reference
• Repairing Texts: Empirical Investigations of Machine Translation Post-Editing Processes

  2001cited by this paper
• Text Categorization with Support Vector Machines: Learning with Many Relevant Features

  1999cited by this paper
• Basic Methods of Probabilistic Context Free Grammars

  1992cited by this paper
• The Estimation of Probabilities: An Essay on Modern Bayesian Methods

  1965cited by this paper

• No citing papers are available for this paper.