Intuition is a method of knowing where individuals rely on their instincts, emotions, and gut feelings to guide their understanding rather than examining objective facts or applying rational logic. It involves accepting a belief as true simply because it inherently feels right or because someone's behavior intuitively seems unusual, prompting the need to critically evaluate whether such subjective knowledge should be fully trusted.

Intuition

This paper proposes metrics to evaluate the quality of automatically generated metaphors not restricted to similes. The metrics are metaphoricity, novelty, comprehensibility, and overall evaluation.

University of Michigan - Ann Arbor

The comprehension of metaphors involves the ability to activate a broader, more flexible set of semantic associations in order to integrate the meanings of the weakly related parts of the metaphor into a meaningful linguistic expression.

Metaphor comprehension

Right hemisphere is thought to be able to comprehend words with multiple meanings and takes on the critical role for at least one important component of metaphor processing. Metaphors presented to the left visual field/right hemisphere are comprehended more accurate and faster than metaphor words presented to the right visual field/left hemisphere. This finding is consistent with both familiar and novel metaphors processing. 

Hemispheric differences

Here are three general categories of hypotheses advanced to explain the underlying cognitive mechanisms:
1. The serial/hierarchical model
2.The parallel/direct processing model
3. The context-dependent model

Hypotheses of underlying mechanisms

Guided by conceptual metaphor theory, this paper proposes to control the generation process by encoding conceptual mappings between cognitive domains to generate meaningful metaphoric expressions.

Metaphor Generation with Conceptual Mappings

Evaluation Metrics for Automatically Generated Metaphorical Expressions

Many target domains, however, cannot be thoroughly investigated by searching a corpus for collocates of target lexemes because not all target language occurs near or next to source domain triggers.
Thus, the ease with which metaphorical structure can be exposed has to do with the relationship between source-domain language and the structural character of the target domain.

Instead of relying on pre-specified semantic fields in the collection of candidate metaphor triggers, I use corpus collocation patterns to gather candidate triggers.

Finding metaphorical triggers through source (not target) domain lexicalization patterns

This study presents a new approach to metaphorical paraphrase generation by masking literal tokens of literal sentences and unmasking them with metaphorical language models.

With this work we present a new metaphorical language generation perspective by transferring literal to metaphorical texts. The transfer concerns the replacement of tokens of different parts of speech, not only the common **verb** type Stowe et al. [2021], Chakrabarty et al. [2021], Yu and Wan [2019], but also **nouns** and **adjectives** (examples shown in Fig. 1).

Learn Before

Related

Learn After