We address for the first time unsupervised training for a translation task
with hundreds of thousands of vocabulary words. We scale up the
expectation-maximization (EM) algorithm to learn a large translation table
without any parallel text or seed lexicon. First, we solve the memory
bottleneck and enforce the sparsity with a simple thresholding scheme for the
lexicon. Second, we initialize the lexicon training with word classes, which
efficiently boosts the performance. Our methods produced promising results on
two large-scale unsupervised translation tasks.

本篇论文首次尝试使用 EM 算法提升词汇表学习并应用于大规模无监督翻译，利用阈值和词类进行序列稀疏化和词汇训练，并在两个大规模无监督翻译任务上取得了良好的结果。

使用稀疏词典和词类进行大词汇翻译的非监督训练

Unsupervised Training for Large Vocabulary Translation Using Sparse  Lexicon and Word Classes

We present two novel datasets for the low-resource language Vietnamese to
assess models of semantic similarity: ViCon comprises pairs of synonyms and
antonyms across word classes, thus offering data to distinguish between
similarity and dissimilarity. ViSim-400 provides degrees of similarity across
five semantic relations, as rated by human judges. The two datasets are
verified through standard co-occurrence and neural network models, showing
results comparable to the respective English datasets.

我们提供了两个新颖的数据集 (ViCon 和 ViSim-400) 来评估越南语这种低资源语言的语义相似性模型，其中 ViCon 包括了各种词类中的同义词和反义词对，ViSim-400 则提供了人工评定的五种语义关系的相似程度，这两个数据集经过标准的共现和神经网络模型验证，显示出与相应英文数据集相媲美的结果。