Corpus Based Methods for Learning Models of Metaphor in Modern Greek

@inproceedings{Pechlivanis2015CorpusBM,
  title={Corpus Based Methods for Learning Models of Metaphor in Modern Greek},
  author={Konstantinos Pechlivanis and Stasinos Konstantopoulos},
  booktitle={SLSP},
  year={2015}
}
In this paper we propose a method for detecting metaphorical usage of content terms based on the hypothesis that metaphors can be detected by being characteristic of a different domain than the one they appear in. We formulate the problem as one of extracting knowledge from text classification models, where the latter have been created using standard text classification techniques without any knowledge of metaphor. We then extract from such models a measure of how characteristic of a domain a… 

References

SHOWING 1-7 OF 7 REFERENCES
CorMet: A Computational, Corpus-Based Conventional Metaphor Extraction System
CorMet is a corpus-based system for discovering metaphorical mappings between concepts. It does this by finding systematic variations in domain-specific selectional preferences, which are inferred
Metaphor Detection through Term Relevance
TLDR
A statistical approach to metaphor detection that utilizes the rarity of novel metaphors, marking words that do not match a text’s typical vocabulary as metaphor candidates and appears to be particularly useful when data is sparse, while its effect diminishes as the amount of training data increases.
A Clustering Approach for Nearly Unsupervised Recognition of Nonliteral Language
In this paper we present TroFi (Trope Finder), a system for automatically classifying literal and nonliteral usages of verbs through nearly unsupervised word-sense disambiguation and clustering
Hunting Elusive Metaphors Using Lexical Resources.
TLDR
This paper proposes algorithms to automatically classify sentences into metaphoric or normal usages, which only need the WordNet and bigram counts, and does not require training.
met*: A Method for Discriminating Matonymy and Metaphor by Computer
  • D. Fass
  • Linguistics
    Comput. Linguistics
  • 1991
TLDR
The met* method is part of Collative Semantics, a semantics for natural language processing, and has been implemented in a computer program called meta5, and some examples of meta5's analysis of metaphor and metonymy are given.
Metaphor Identification as Interpretation
TLDR
A novel method is presented that performs metaphor identification through its interpretation, being the first one in NLP to combine the two tasks in one step and outperforms the previous approaches to metaphor identification both in terms of accuracy and coverage, as well as providing an interpretation for each identified expression.
Boilerplate detection using shallow text features
TLDR
This paper analyzes a small set of shallow text features for classifying the individual text elements in a Web page and derives a simple and plausible stochastic model for describing the boilerplate creation process.