Unsupervised Bilingual Dictionary Induction methods based on the
initialization and the self-learning have achieved great success in similar
language pairs, e.g., English-Spanish. But they still fail and have an accuracy
of 0% in many distant language pairs, e.g., English-Japanese. In this work, we
show that this failure results from the gap between the actual initialization
performance and the minimum initialization performance for the self-learning to
succeed. We propose Iterative Dimension Reduction to bridge this gap. Our
experiments show that this simple method does not hamper the performance of
similar language pairs and achieves an accuracy of 13.64~55.53% between English
and four distant languages, i.e., Chinese, Japanese, Vietnamese and Thai.

本研究针对无监督双语词典归纳在类似语言对中表现良好但在远距离语言对中表现不佳的问题，提出迭代降维方法以此来弥补自学习最小初始化性能和实际初始化性能之间的差距，其实验结果表明这种简单的方法在类似语言对中不会影响性能，并在英语与中文，日语，越南语和泰语四种较远距离语言之间实现了 13.64-55.53% 的准确率。

一种简单而有效的稳健非监督双语词典归纳方法

A Simple and Effective Approach to Robust Unsupervised Bilingual  Dictionary Induction

One of the central knowledge sources of an information extraction system is a
dictionary of linguistic patterns that can be used to identify the conceptual
content of a text. This paper describes CRYSTAL, a system which automatically
induces a dictionary of "concept-node definitions" sufficient to identify
relevant information from a training corpus. Each of these concept-node
definitions is generalized as far as possible without producing errors, so that
a minimum number of dictionary entries cover the positive training instances.
Because it tests the accuracy of each proposed definition, CRYSTAL can often
surpass human intuitions in creating reliable extraction rules.

本文介绍了 CRYSYAL 系统，它自动归纳了足以从训练语料库中识别出相关信息的 “概念节点定义” 字典，通过测试每个建议的定义的准确性，因此，CRYSYAL 通常比人类直觉更能够创建可靠的提取规则。