Feature-based Decipherment for Large Vocabulary Machine Translation
This work addresses machine translation for closely related languages, but it is incremental as it builds on existing decipherment models with feature-based improvements.
The authors tackled the problem of machine translation for closely related languages by developing a log-linear model with orthographic similarity features, which outperformed existing generative decipherment models and scaled to large vocabularies.
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 approximate inference via MCMC sampling and contrastive divergence. Our results show that the proposed log-linear model with contrastive divergence scales to large vocabularies and outperforms the existing generative decipherment models by exploiting the orthographic features.