Exploring Metaphorical Senses and Word Representations for Identifying Metonyms
This work addresses a specific NLP task (metonym detection) for researchers, but it is incremental as it adapts existing metaphor features to a related problem.
The paper tackled the problem of detecting metonyms (figurative words) by applying metaphor recognition features to metonym identification, achieving 86.45% accuracy on location metonyms using the ACL SemEval 2007 Task 8 dataset.
A metonym is a word with a figurative meaning, similar to a metaphor. Because metonyms are closely related to metaphors, we apply features that are used successfully for metaphor recognition to the task of detecting metonyms. On the ACL SemEval 2007 Task 8 data with gold standard metonym annotations, our system achieved 86.45% accuracy on the location metonyms. Our code can be found on GitHub.