Sciweavers

162 search results - page 5 / 33
» Automatic Discovery of Feature Sets for Dependency Parsing
Sort
View
BMCBI
2006
127views more  BMCBI 2006»
14 years 9 months ago
Automatic discovery of cross-family sequence features associated with protein function
Background: Methods for predicting protein function directly from amino acid sequences are useful tools in the study of uncharacterised protein families and in comparative genomic...
Markus Brameier, Josien Haan, Andrea Krings, Rober...
79
Voted
ACL
2012
13 years 21 hour ago
Selective Sharing for Multilingual Dependency Parsing
We present a novel algorithm for multilingual dependency parsing that uses annotations from a diverse set of source languages to parse a new unannotated language. Our motivation i...
Tahira Naseem, Regina Barzilay, Amir Globerson
CICLING
2008
Springer
14 years 11 months ago
Semantic and Syntactic Features for Dutch Coreference Resolution
We investigate the effect of encoding additional semantic and syntactic information sources in a classification-based machine learning approach to the task of coreference resolutio...
Iris Hendrickx, Véronique Hoste, Walter Dae...
CICLING
2008
Springer
14 years 11 months ago
Verb Class Discovery from Rich Syntactic Data
Abstract. Previous research has shown that syntactic features are the most informative features in automatic verb classification. We investigate their optimal characteristics by co...
Lin Sun, Anna Korhonen, Yuval Krymolowski
EMNLP
2007
14 years 11 months ago
Single Malt or Blended? A Study in Multilingual Parser Optimization
We describe a two-stage optimization of the MaltParser system for the ten languages in the multilingual track of the CoNLL 2007 shared task on dependency parsing. The first stage...
Johan Hall, Jens Nilsson, Joakim Nivre, Gülse...