Corpus ID: 11718980

Feature-based Decipherment for Large Vocabulary Machine Translation

@article{Naim2015FeaturebasedDF,
  title={Feature-based Decipherment for Large Vocabulary Machine Translation},
  author={Iftekhar Naim and Daniel Gildea},
  journal={ArXiv},
  year={2015},
  volume={abs/1508.02142}
}
  • Iftekhar Naim, Daniel Gildea
  • Published 2015
  • Computer Science
  • ArXiv
  • Orthographic similarities across languages provide a strong signal for probabilistic decipherment, especially for closely related language pairs. The existing decipherment models, however, are not well-suited for exploiting these orthographic similarities. We propose a log-linear model with latent variables that incorporates orthographic similarity features. Maximum likelihood training is computationally expensive for the proposed log-linear model. To address this challenge, we perform… CONTINUE READING
    2 Citations
    Deciphering Related Languages
    • 17
    • PDF
    Unsupervised Alignment of Natural Language with Video
    • 1

    References

    SHOWING 1-10 OF 20 REFERENCES
    Scalable Decipherment for Machine Translation via Hash Sampling
    • 17
    • Highly Influential
    • PDF
    Large Scale Decipherment for Out-of-Domain Machine Translation
    • Qing Dou, Kevin Knight
    • Computer Science
    • EMNLP-CoNLL
    • 2012
    • 61
    • Highly Influential
    • PDF
    Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation
    • 17
    • PDF
    Unsupervised Word Alignment with Arbitrary Features
    • 57
    • PDF
    EM Decipherment for Large Vocabularies
    • 9
    • Highly Influential
    • PDF
    A Computational Approach to Deciphering Unknown Scripts
    • 45
    • PDF
    Painless Unsupervised Learning with Features
    • 224
    • PDF
    Prototype-Driven Learning for Sequence Models
    • 212
    • PDF
    Conditional Random Field Autoencoders for Unsupervised Structured Prediction
    • 65
    • PDF