.png){kind=icon}
返回
Feature-Based Decipherment for Machine Translation
.png){kind=icon}
OA
AI
DOI：10.1162/coli_a_00326.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
5.3
论文数:
837
被引数:
2.7K
机构
引用论文
.png){kind=icon}
分享收藏分享收藏
查看更多内容