Corpus ID: 10129558

Statistical Machine Translation of Texts with Misspelled Words

  title={Statistical Machine Translation of Texts with Misspelled Words},
  author={N. Bertoldi and M. Cettolo and M. Federico},
  • N. Bertoldi, M. Cettolo, M. Federico
  • Published in HLT-NAACL 2010
  • Computer Science
  • This paper investigates the impact of misspelled words in statistical machine translation and proposes an extension of the translation engine for handling misspellings. The enhanced system decodes a word-based confusion network representing spelling variations of the input text. We present extensive experimental results on two translation tasks of increasing complexity which show how misspellings of different types do affect performance of a statistical machine translation decoder and to… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Dealing with Input Noise in Statistical Machine Translation
    • 12
    • Highly Influenced
    • PDF
    Five Shades of Noise: Analyzing Machine Translation Errors in User-Generated Text
    • 11
    • PDF
    CMU Haitian Creole-English Translation System for WMT 2011
    • 7
    • PDF
    Adapting a WSJ trained part-of-speech tagger to noisy text: preliminary results
    • 31
    Measuring the Impact of Spelling Errors on the Quality of Machine Translation
    • 2
    • Highly Influenced
    • PDF


    Publications referenced by this paper.
    Moses: Open Source Toolkit for Statistical Machine Translation
    • 5,238
    • PDF
    Using Noisy Bilingual Data for Statistical Machine Translation
    • 16
    • PDF
    Correcting real-word spelling errors by restoring lexical cohesion
    • 187
    • PDF
    Pronunciation Modeling for Improved Spelling Correction
    • 211
    • PDF
    SRILM - an extensible language modeling toolkit
    • 4,782
    • PDF
    Probability scoring for spelling correction
    • 178