Identifying semantic equivalence for multi-document summarisation

Authors:
Eamonn Newman;Joe Carthy;John Dunnion;Nicola Stokes
Affiliations:
School of Computer Science and Informatics, University College Dublin, Belfield, Dublin 4, Ireland;School of Computer Science and Informatics, University College Dublin, Belfield, Dublin 4, Ireland;School of Computer Science and Informatics, University College Dublin, Belfield, Dublin 4, Ireland;NICTA Victoria Laboratory, Department of Computer Science and Software Engineering, University of Melbourne, Melbourne, Australia
Venue:
Artificial Intelligence Review
Year:
2006

Citing 7
Cited 0

Robust textual inference via learning and abductive reasoning

AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 3
Proceedings of the ACL Workshop on Empirical Modeling of Semantic Equivalence and Entailment

EMSEE '05 Proceedings of the ACL Workshop on Empirical Modeling of Semantic Equivalence and Entailment
Classification of semantic relations by humans and machines

EMSEE '05 Proceedings of the ACL Workshop on Empirical Modeling of Semantic Equivalence and Entailment
Measuring the semantic similarity of texts

EMSEE '05 Proceedings of the ACL Workshop on Empirical Modeling of Semantic Equivalence and Entailment
What syntax can contribute in the entailment task

MLCW'05 Proceedings of the First international conference on Machine Learning Challenges: evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual Entailment
Textual entailment recognition based on dependency analysis and wordnet

MLCW'05 Proceedings of the First international conference on Machine Learning Challenges: evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual Entailment
An inference model for semantic entailment in natural language

MLCW'05 Proceedings of the First international conference on Machine Learning Challenges: evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual Entailment

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe Semantic Equivalence and Textual Entailment Recognition, and outline a system which uses a number of lexical, syntactic and semantic features to classify pairs of sentences as "semantically equivalent". We describe an experiment to show how syntactic and semantic features improve the performance of an earlier system, which used only lexical features. We also outline some areas for future work.