It has been established that incorporating word cluster features derived from large unlabeled corpora can significantly improve prediction of linguistic structure. While previous work has focused primarily on English, we extend these results to other languages along two dimensions. First, we show that these results hold true for a number of languages across families. Second, and more interestingly, we provide an algorithm for inducing cross-lingual clusters and we show that features derived from these clusters significantly improve the accuracy of cross-lingual structure prediction. Specifically, we show that by augmenting direct-transfer systems with cross-lingual cluster features, the relative error of delexicalized dependency parsers, trained on English treebanks and transferred to foreign languages, can be reduced by up to 13%. When applying the same method to direct transfer of named-entity recognizers, we observe relative improvements of up to 26%.

We present novel methods to construct compact natural language lexicons within a graphbased semi-supervised learning framework, an attractive platform suited for propagating soft labels onto new natural language types from seed data. To achieve compactness, we induce sparse measures at graph vertices by incorporating sparsity-inducing penalties in Gaussian and entropic pairwise Markov networks constructed from labeled and unlabeled data. Sparse measures are desirable for high-dimensional multi-class learning problems such as the induction of labels on natural language types, which typically associate with only a few labels. Compared to standard graph-based learning methods, for two lexicon expansion problems, our approach produces significantly smaller lexicons and obtains better predictive performance. 1