The effects of semantic annotations on precision parse ranking

Authors:
Andrew MacKinlay;Rebecca Dridan;Diana McCarthy;Timothy Baldwin
Affiliations:
University of Melbourne, Australia and NICTA Victoria Research Laboratories, University of Melbourne, Australia;University of Oslo, Norway;Computational Linguistics and Phonetics, Saarland University, Germany;University of Melbourne, Australia and NICTA Victoria Research Laboratories, University of Melbourne, Australia
Venue:
SemEval '12 Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation
Year:
2012

Citing 19
Cited 1

WordNet: a lexical database for English

Communications of the ACM
Building a large annotated corpus of English: the penn treebank

Computational Linguistics - Special issue on using large corpora: II
On building a more efficient grammar by exploiting types

Natural Language Engineering
A compact architecture for dialogue management based on scripts and meta-outputs

ANLC '00 Proceedings of the sixth conference on Applied natural language processing
TnT: a statistical part-of-speech tagger

ANLC '00 Proceedings of the sixth conference on Applied natural language processing
A maximum-entropy-inspired parser

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Three generative, lexicalised models for statistical parsing

ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
Automatic retrieval and clustering of similar words

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Efficient deep processing of Japanese

COLING '02 Proceedings of the 3rd workshop on Asian language resources and international standardization - Volume 12
A comparison of algorithms for maximum entropy parameter estimation

COLING-02 proceedings of the 6th conference on Natural language learning - Volume 20
Parsing the WSJ using CCG and log-linear models

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Finding predominant word senses in untagged text

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Design of a multi-lingual, parallel-processing statistical parsing engine

HLT '02 Proceedings of the second international conference on Human Language Technology Research
Exploiting semantic information for HPSG parse selection

DeepLP '07 Proceedings of the Workshop on Deep Linguistic Processing
Broad-coverage sense disambiguation and information extraction with a supersense sequence tagger

EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Efficiency in unification-based N-best parsing

IWPT '07 Proceedings of the 10th International Conference on Parsing Technologies
Improving dependency parsing with semantic classes

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Cross-Domain Effects on Parse Selection for Precision Grammars

Research on Language and Computation
Parser evaluation using elementary dependency matching

IWPT '11 Proceedings of the 12th International Conference on Parsing Technologies

Word sense and semantic relations in noun compounds

ACM Transactions on Speech and Language Processing (TSLP) - Special issue on multiword expressions: From theory to practice and use, part 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

We investigate the effects of adding semantic annotations including word sense hypernyms to the source text for use as an extra source of information in HPSG parse ranking for the English Resource Grammar. The semantic annotations are coarse semantic categories or entries from a distributional thesaurus, assigned either heuristically or by a pre-trained tagger. We test this using two test corpora in different domains with various sources of training data. The best reduces error rate in dependency F-score by 1% on average, while some methods produce substantial decreases in performance.