A computational model of metaphor interpretation
A computational model of metaphor interpretation
Selection and information: a class-based approach to lexical relationships
Selection and information: a class-based approach to lexical relationships
Automatic labeling of semantic roles
Computational Linguistics
met*: a method for discriminating metonymy and metaphor by computer
Computational Linguistics
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
CorMet: a computational, corpus-based conventional metaphor extraction system
Computational Linguistics
Accurate unlexicalized parsing
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
The Proposition Bank: An Annotated Corpus of Semantic Roles
Computational Linguistics
RelEx---Relation extraction using dependency parse trees
Bioinformatics
Hunting elusive metaphors using lexical resources
FigLanguages '07 Proceedings of the Workshop on Computational Approaches to Figurative Language
Dependency-based semantic role labeling of PropBank
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Open text semantic parsing using FrameNet and WordNet
HLT-NAACL--Demonstrations '04 Demonstration Papers at HLT-NAACL 2004
ScaNaLU '06 Proceedings of the Third Workshop on Scalable Natural Language Understanding
Computational metaphor identification to foster critical thinking and creativity
Computational metaphor identification to foster critical thinking and creativity
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Hi-index | 0.00 |
Most computational approaches to metaphor have focused on discerning between metaphorical and literal text. Recent work on computational metaphor identification (CMI) instead seeks to identify overarching conceptual metaphors by mapping selectional preferences between source and target corpora. This paper explores using semantic role labeling (SRL) in CMI. Its goals are two-fold: first, to demonstrate that semantic roles can effectively be used to identify conceptual metaphors, and second, to compare SRL to the current use of typed dependency parsing in CMI. The results show that SRL can be used to identify potential metaphors and that it overcomes some of the limitations of using typed dependencies, but also that SRL introduces its own set of complications. The paper concludes by suggesting future directions, both for evaluating the use of SRL in CMI, and for fostering critical and creative thinking about metaphors.