Literal and Metaphorical Senses in Compositional Distributional Semantic ModelsLiteral and Metaphorical Senses in Compositional Distributional Semantic ModelsGutiérrez, E. Dario and Shutova, Ekaterina and Marghetis, Tyler and Bergen, Benjamin2016
Paper summarymarekThe paper investigates compositional semantic models specialised for metaphors.
https://i.imgur.com/OnoJK3h.png
They construct a dataset of 8592 adjective-noun phrases, covering 23 different adjectives, annotated for being metaphorical or literal. They then train compositional models to predict the phrase vector based on the noun vector, as a linear combination with an adjective-specific weight matrix. They show that it’s better to learn separate adjective matrices for literal and metaphorical uses of each adjective, even though the amount of training data is smaller.
Literal and Metaphorical Senses in Compositional Distributional Semantic Models
Gutiérrez, E. Dario
and
Shutova, Ekaterina
and
Marghetis, Tyler
and
Bergen, Benjamin
Association for Computational Linguistics - 2016 via Local Bibsonomy
Keywords:
dblp
The paper investigates compositional semantic models specialised for metaphors.
https://i.imgur.com/OnoJK3h.png
They construct a dataset of 8592 adjective-noun phrases, covering 23 different adjectives, annotated for being metaphorical or literal. They then train compositional models to predict the phrase vector based on the noun vector, as a linear combination with an adjective-specific weight matrix. They show that it’s better to learn separate adjective matrices for literal and metaphorical uses of each adjective, even though the amount of training data is smaller.