arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1508.02142cs.CL
收藏

大词汇量机器翻译中基于语义的译解

Feature-based Decipherment for Large Vocabulary Machine Translation

University of Rochester(罗切斯特大学)

Iftekhar Naim, Daniel Gildea

摘要:

跨语言的正字法相似性为概率破译提供了强有力的信号,特别是对于密切相关的语言对。现有的解码模型,但是,不太适合利用这些正字法的相似性。我们提出了一个对数线性模型的潜变量,采用正交相似性功能。对于所提出的对数线性模型,最大似然训练在计算上昂贵。为了解决这一挑战,我们通过MCMC采样和对比发散进行近似推理。我们的研究结果表明,提出的对数线性模型与对比发散规模大的词汇,并通过利用正字法功能优于现有的生成式解密模型。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑