Feature-based Decipherment for Large Vocabulary Machine Translation

08/10/2015
by   Iftekhar Naim, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/05/2017

Building Morphological Chains for Agglutinative Languages

In this paper, we build morphological chains for agglutinative languages...
research
11/28/2017

On the correspondence of deviances and maximum likelihood and interval estimates from log-linear to logistic regression modelling

Consider a set of categorical variables P where at least one, denoted by...
research
05/16/2016

Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing

This paper describes the submission of the AMU (Adam Mickiewicz Universi...
research
09/26/2017

Learning Multi-grid Generative ConvNets by Minimal Contrastive Divergence

This paper proposes a minimal contrastive divergence method for learning...
research
05/06/2014

Training Restricted Boltzmann Machine by Perturbation

A new approach to maximum likelihood learning of discrete graphical mode...
research
11/03/2022

Can RBMs be trained with zero step contrastive divergence?

Restricted Boltzmann Machines (RBMs) are probabilistic generative models...
research
09/21/2017

Learning RBM with a DC programming Approach

By exploiting the property that the RBM log-likelihood function is the d...

Please sign up or login with your details

Forgot password? Click here to reset