This paper describes a series of French semantic role labelling experiments which show that a small set of manually annotated training data is superior to a much larger set containing semantic role labels which have been projected from a source language via word alignment. Using universal part-of-speech tags and dependencies makes little difference over the original fine-grained tagset and depe...

We prove an analog of the classical Hartogs extension theorem for certain (possibly unbounded) domains on coverings of strongly pseudoconvex manifolds. Our result is related to a problem posed in the paper of Gromov, Henkin and Shubin [GHS] on holomorphic L2 functions on coverings of pseudoconvex manifolds. Previously in [Br3] similar results were established for some domains on coverings of St...