Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/151246
Title: Metaphoricity detection in adjective-noun pairs
Other Titles: Detección de metaforicidad en pares adjetivo-sustantivo
Author: Torres Rivera, Andrés  
Oliver, Antoni  
Coll-Florit, Marta  
Abstract: In this paper we propose a neural network approach to detect the metaphoricity of Adjective-Noun pairs using pre-trained word embeddings and word similarity using dot product. We found that metaphorical word pairs tend to have a lower dot product score while literal pairs a higher score. On this basis, we compared seven optimizers and two activation functions, from which the best performing pairs obtained an accuracy score of 97.69% and 97.74%, which represents an improvement of 6% over other current approaches.
Torres Rivera, A.[Andrés], Oliver, A. [Antoni]& Coll-Florit, M. [Marta]. (2020). Metaphoricity Detection in Adjective-Noun Pairs. Procesamiento del lenguaje natural, 64(null), 53-60. doi: 10.26342/2020-64-6
Keywords: NLP
metaphor
Word Embeddings
deep learning
DOI: https://doi.org/10.26342/2020-64-6
Document type: info:eu-repo/semantics/article
Version: info:eu-repo/semantics/publishedVersion
Issue Date: Jan-2020
Publication license: http://creativecommons.org/licenses/by/3.0/es/  
Appears in Collections:Articles
Articles cientÍfics

Files in This Item:
File Description SizeFormat 
2020-MetaphocicityDection-Rivera_Oliver_CollFlorit.pdf1,13 MBAdobe PDFThumbnail
View/Open
Share:
Export:
View statistics

This item is licensed under aCreative Commons License Creative Commons