Manually performed treebanking is an expensive effort compared with automatic annotation. In return, manual treebanking is generally believed to provide higherquality/value syntactic annotation than automatic methods. Unfortunately, there is little or no empirical evidence for or against this belief, though arguments have been voiced for the high degree of subjectivity in other levels of lingui...

Similarity between words is becoming a generic problem for many applications of computational linguistics, and computing word similarities is determined by word representations. Inspired by the analogies between words and lymphocytes, a lymphocyte-style word representation is proposed. The word representation is built on the basis of dependency syntax of sentences and represent word context as ...

We describe the methods and resources used to build FinnTreeBank-3, a 76.4 million token corpus of Finnish with automatically produced morphological and dependency syntax analyses. Starting from a definition of the target dependency scheme, we show how existing resources are transformed to conform to this definition and subsequently used to develop a parsing pipeline capable of processing a lar...

In the paper [MTT] a conceptuel description of compactifications of moduli spaces of stable vector bundles on surfaces has been given, whose boundaries consist of vector bundles on trees of sufaces. In this article a typical basic case for the projective plane is described explicitly including the constrution of a relevant Kirwan blow up.

For several languages only potentially non-projective dependency parses are readily available. Projectivizing the parses and utilizing them in syntax-based translation systems often yields particularly bad translation results indicating that those translation models cannot properly utilize such information. We demonstrate that our system based on multi bottom-up tree transducers, which can nati...

This paper describes a treebanking project for Hindi/Urdu. We are annotating dependency syntax, lexical predicate-argument structure, and phrase structure syntax in a coordinated and partly automated manner. The paper focuses on choices in syntactic representation, and the stages we think are most appropriate for annotating differnt types of information.

A generative statistical model of dependency syntax is proposed based on Tesni ere's classical theory. It provides a stochastic formalization of the original model of syntactic structure and augments it with a model of the string realization process, the latter which is lacking in Tesni ere's original work. The resulting theory models crossing dependency links, discontinuous nuclei and string m...

We introduce a framework for lightweight dependency syntax annotation. Our formalism builds upon the typical representation for unlabeled dependencies, permitting a simple notation and annotation workflow. Moreover, the formalism encourages annotators to underspecify parts of the syntax if doing so would streamline the annotation process. We demonstrate the efficacy of this annotation on three ...