The paper presents a corpus-based method for finding metaphorically used lexemes and prevailing semantico-conceptual source domains, given a target domain corpus. It is exemplified by a case study on the target domain of European politics, based on a French 800,000 token corpus. 1

Using metaphor-annotated material that is sufficiently representative of the topical composition of a similar-length document in a large background corpus, we show that words expressing a discourse-wide topic of discussion are less likely to be metaphorical than other words in a document. Our results suggest that to harvest metaphors more effectively, one is advised to consider words that do not represent a discourse topic. Traditionally, metaphor detectors use the observation that a metaphorically used item creates a local incongruity because there is a violation of a selectional restriction, such as providing a non-vehicle object to the verb derail in Protesters derailed the conference. Current state of art in metaphor detection therefore tends to be “localistic ” – the distributional profile of the target word in its immediate grammatical or collocational context in a background corpus or a database like WordNet is used to determine metaphoricity

Psycholinguistic studies of metaphor processing must control their stimuli not just for word frequency but also for the frequency with which a term is used metaphorically. Thus, we consider the task of metaphor frequency estimation, which predicts how often target words will be used metaphorically. We develop metaphor classifiers which represent metaphorical domains through Latent Dirichlet Allocation, and apply these classifiers to the target words, aggregating their decisions to estimate the metaphorical frequencies. Training on only 400 sentences, our models are able to achieve 61.3 % accuracy on metaphor classification and 77.8 % accuracy on HIGH vs. LOW metaphorical frequency estimation. 1

We present a novel approach to automatic metaphor identification in unrestricted text. Starting from a small seed set of manually annotated metaphorical expressions, the system is capable of harvesting a large number of metaphors of similar syntactic structure from a corpus. Our method is distinguished from previous work in that it does not employ any hand-crafted knowledge, other than the initial seed set, but, in contrast, captures metaphoricity by means of verb and noun clustering. Being the first to employ unsupervised methods for metaphor identification, our system operates with the precision of 0.79. 1

The heading figurative language subsumes multiple phenomena that can be used to perform most linguistic functions including predication, modification, and reference. Figurative language can tap into conceptual and linguistic knowledge (as in the case of idioms, metaphor, and some metonymies) as well as evoke pragmatic factors in interpretation (as in indirect speech acts, humor, irony, or

Abstract. This paper concerns metaphor resource creation. It provides an account of methods used, problems discovered, and insights gained at the Hamburg Metaphor Database project, intended to inform similar resource creation initiatives, as well as future metaphor processing algorithms. After introducing the project, the theoretical underpinnings that motivate the subdivision of represented information into a conceptual and a lexical level are laid out. The acquisition of metaphor attestations from electronic corpora is explained, and annotation practices as well as database contents are evaluated. The paper concludes with an overview of related projects and an outline of possible future work.

Metaphor is highly frequent in language, which makes its computational processing indispensable for real-world NLP applications addressing semantic tasks. Previous approaches to metaphor modelling rely on task-specific hand-coded knowledge and operate on a limited domain or a subset of phenomena. We present the first integrated open-domain statistical model of metaphor processing in unrestricted text. Our method first identifies metaphorical expressions in running text and then paraphrases them with their literal paraphrases. Such a text-to-text model of metaphor interpretation is compatible with other NLP applications that can benefit from metaphor resolution. Our approach is minimally supervised, it relies on the state-of-the-art parsing and lexical acquisition technologies (distributional clustering and selectional preference induction) and operates with a high accuracy. 1.