We train one multilingual model for dependency parsing and use it to parse sentences in
several languages. The parsing model uses (i) multilingual word clusters and …

We use Bayesian optimization to learn curricula for word representation learning, optimizing
performance on downstream tasks that depend on the learned representations as features …

We introduce QVEC-CCA--an intrinsic evaluation metric for word vector representations
based on correlations of learned vectors with features extracted from linguistic resources …

I explore the hypothesis that the universal properties of human languages can be explained
in terms of efficient communication given fixed human information processing constraints. I …

Universal Dependencies (UD) is a project that is developing crosslinguistically consistent
treebank annotation for many languages, with the goal of facilitating multilingual parser …

Word representations are mathematical objects that capture a word's meaning and its
grammatical properties in a way that can be read and understood by computers. Word …

Morpho-syntactic lexicons provide information about the morphological and syntactic roles
of words in a language. Such lexicons are not available for all languages and even when …

The central goal of this thesis is to bridge the divide between theoretical linguistics—the
scientific inquiry of language—and applied data-driven statistical language processing, to …

We compare two annotation styles, Prague dependencies and Universal Stanford
Dependencies, in their adequacy for parsing. We specifically focus on comparing the …

Text compression is needed to reduce the space required to store information contained in
the text and the amount of time needed to transmit that information. Compression-based …