Sciweavers

ACL
2010
13 years 9 months ago
Efficient Third-Order Dependency Parsers
We present algorithms for higher-order dependency parsing that are "third-order" in the sense that they can evaluate substructures containing three dependencies, and &qu...
Terry Koo, Michael Collins
COLING
2000
14 years 24 days ago
Automatic Extraction of Subcategorization Frames for Czech
We present some novel machine learning techniques for the identification of subcategorization information for verbs in Czech. We compare three different statistical techniques app...
Anoop Sarkar, Daniel Zeman
ACL
2006
14 years 26 days ago
Graph Transformations in Data-Driven Dependency Parsing
Transforming syntactic representations in order to improve parsing accuracy has been exploited successfully in statistical parsing systems using constituency-based representations...
Jens Nilsson, Joakim Nivre, Johan Hall
LREC
2008
83views Education» more  LREC 2008»
14 years 27 days ago
Validating the Quality of Full Morphological Annotation
In our paper we present a methodology used for low-cost validation of quality of Part-of-Speech annotation of the Prague Dependency Treebank based on multiple re-annotation of dat...
Drahomíra "johanka" Spoustová, Pavel...
LREC
2010
149views Education» more  LREC 2010»
14 years 27 days ago
Annotation of Morphological Meanings of Verbs Revisited
Meanings of morphological categories are an indispensable component of representation of sentence semantics. In the Prague Dependency Treebank 2.0, sentence semantics is represent...
Jarmila Panevová, Magda Sevcíkov&aac...
LREC
2010
144views Education» more  LREC 2010»
14 years 27 days ago
Mapping between Dependency Structures and Compositional Semantic Representations
This paper investigates the mapping between two semantic formalisms, namely the tectogrammatical layer of the Prague Dependency Treebank 2.0 (PDT) and (Robust) Minimal Recursion S...
Max Jakob, Markéta Lopatková, Valia ...
ACL
2008
14 years 28 days ago
Simple Semi-supervised Dependency Parsing
We present a simple and effective semisupervised method for training dependency parsers. We focus on the problem of lexical representation, introducing features that incorporate w...
Terry Koo, Xavier Carreras, Michael Collins