• Publications
  • Influence
chrF: character n-gram F-score for automatic MT evaluation
TLDR
We propose the use of character n-gram F-score for automatic evaluation of machine translation output. Expand
  • 209
  • 26
  • PDF
chrF++: words helping character n-grams
TLDR
Character n-gram F-score is shown to correlate very well with human relative rankings of different machine translation outputs, especially for morphologically rich target languages. Expand
  • 38
  • 11
  • PDF
Towards Automatic Error Analysis of Machine Translation Output
TLDR
We propose a framework for automatic error analysis and classification based on the identification of actual erroneous words using the algorithms for computation of Word Error Rate and Position-independent word Error Rate (PER), which is just a very first step towards development of automatic evaluation measures that provide more specific information of certain translation problems. Expand
  • 94
  • 7
  • PDF
Towards the Use of Word Stems and Suffixes for Statistical Machine Translation
TLDR
We present methods for improving the quality of translation from an inflected language into English by making use of part-of-speech tags and word stems and suffixes in the source language. Expand
  • 97
  • 7
  • PDF
Statistical Machine Translation of German Compound Words
TLDR
In this work, we investigate and compare different strategies for the treatment of German compound words in statistical machine translation systems. Expand
  • 66
  • 7
  • PDF
Hjerson: An Open Source Tool for Automatic Error Classification of Machine Translation Output
  • Maja Popovic
  • Computer Science
  • Prague Bull. Math. Linguistics
  • 1 October 2011
TLDR
Hjerson: An Open Source Tool for Automatic Error Classification of Machine Translation Output We describe Hjerson, a tool for automatic classification of errors in machine translation output. Expand
  • 86
  • 6
  • PDF
Class error rates for evaluation of machine translation output
TLDR
We investigate the use of error classification results for automatic evaluation of machine translation output. Expand
  • 14
  • 6
  • PDF
Word Error Rates: Decomposition over POS classes and Applications for Error Analysis
TLDR
We propose a novel method for obtaining more details about actual translation errors in the generated output by introducing the decomposition of Word Error Rate (Wer) and Position independent word Error rate (Per) over different Part-of-Speech (Pos) classes. Expand
  • 87
  • 5
  • PDF
Relations between different types of post-editing operations, cognitive effort and temporal effort
TLDR
This work investigates five types of post-edit operations and their relation with cognitive post-editing effort (quality level) and postediting time. Expand
  • 20
  • 4
  • PDF
Evaluate with Confidence Estimation: Machine ranking of translation outputs using grammatical features
TLDR
We present a pilot study on an evaluation method which is able to rank translation outputs with no reference translation, given only their source sentence. Expand
  • 36
  • 3
  • PDF