Empirical evaluations of animacy annotation

Authors:
Lilja Øvrelid
Affiliations:
University of Potsdam, Germany
Venue:
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Year:
2009

Citing 9
Cited 1

Approximate statistical tests for comparing supervised classification learning algorithms

Neural Computation
Automatic verb classification based on statistical distributions of argument structure

Computational Linguistics
Semi-supervised verb class discovery using noisy features

CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
CoNLL-X shared task on multilingual dependency parsing

CoNLL-X '06 Proceedings of the Tenth Conference on Computational Natural Language Learning
Labeled pseudo-projective dependency parsing with support vector machines

CoNLL-X '06 Proceedings of the Tenth Conference on Computational Natural Language Learning
Linguistic features in data-driven dependency parsing

CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
Animacy encoding in English: why and how

DiscAnnotation '04 Proceedings of the 2004 ACL Workshop on Discourse Annotation
NP animacy identification for anaphora resolution

Journal of Artificial Intelligence Research
Climbing the path to grammar: a maximum entropy model of subject/object learning

PMHLA '05 Proceedings of the Workshop on Psychocomputational Models of Human Language Acquisition

Extracting human Spanish nouns

TSD'10 Proceedings of the 13th international conference on Text, speech and dialogue

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article presents empirical evaluations of aspects of annotation for the linguistic property of animacy in Swedish, ranging from manual human annotation, automatic classification and, finally, an external evaluation in the task of syntactic parsing. We show that a treatment of animacy as a lexical semantic property of noun types enables generalization over distributional properties of these nouns which proves beneficial in automatic classification and furthermore gives significant improvements in terms of parsing accuracy for Swedish, compared to a state-of-the-art baseline parser with gold standard animacy information.