@article{naim-etal-2018-feature,
    title = "Feature-Based Decipherment for Machine Translation",
    author = "Naim, Iftekhar  and
      Riley, Parker  and
      Gildea, Daniel",
    journal = "Computational Linguistics",
    volume = "44",
    number = "3",
    month = sep,
    year = "2018",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/J18-3006/",
    doi = "10.1162/coli_a_00326",
    pages = "525--546",
    abstract = "Orthographic similarities across languages provide a strong signal for unsupervised probabilistic transduction (decipherment) 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 approximate inference via Markov chain Monte Carlo sampling and contrastive divergence. Our results show that the proposed log-linear model with contrastive divergence outperforms the existing generative decipherment models by exploiting the orthographic features. The model both scales to large vocabularies and preserves accuracy in low- and no-resource contexts."
}