Detecting Metonymic Expressions with Associative Information from Words

Teraoka, Takehiro; Okamoto, Jun; Ishizaki, Shun

doi:10.1016/j.sbspro.2011.10.588

Search citation statements

Order By: Relevance

Paper Sections

Select...

Metonymy Resolution Of Classes1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2021

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have explored different hand-crafted features for metonymy detection such as co-occurrence, collocation and grammatical features (Markert and Hahn, 2002;Markert and Nissim, 2002;Nissim and Markert, 2003), associative information (Teraoka et al, 2011;Teraoka, 2016), and selectional preference features (Nastase and Strube, 2009;Nastase et al, 2012). Gritta et al (2017) employ a neural-networkbased model that uses the context words of the PMW to identify whether the PMW is literal or metonymic.…”

Section: Metonymy Resolution Of Classesmentioning

confidence: 99%

Impact of Target Word and Context on End-to-End Metonymy Detection

Mathews¹,

Strube²

2021

Preprint

View full text Add to dashboard Cite

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.

show abstract