Feature-Based Decipherment for Machine Translation

• Main Authors: Iftekhar Naim, Parker Riley, Daniel Gildea
• Format: Article
• Language: English
• Published: The MIT Press 2018-09-01
• Series: Computational Linguistics
• Online Access: https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00326

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.