Impact of Target Word and Context on End-to-End Metonymy Detection
This work addresses metonymy detection for natural language processing, but it is incremental as it extends existing methods to full-sentence labeling.
The paper tackled metonymy detection by reformulating it as a sequence labeling task to disambiguate every word in a sentence, finding that context words are more relevant than target words, with entity types associated with domain-specific context words being easier to solve.
Metonymy is a figure of speech in which an entity is referred to by another related entity. The task of metonymy detection aims to distinguish metonymic tokens from literal ones. Until now, metonymy detection methods attempt to disambiguate only a single noun phrase in a sentence, typically location names or organization names. In this paper, we disambiguate every word in a sentence by reformulating metonymy detection as a sequence labeling task. We also investigate the impact of target word and context on metonymy detection. We show that the target word is less useful for detecting metonymy in our dataset. On the other hand, the entity types that are associated with domain-specific words in their context are easier to solve. This shows that the context words are much more relevant for detecting metonymy.