Skip to content
conftrace_
2018 NAACL NAACL 2018

Detecting Figurative Word Occurrences Using Recurrent Neural Networks

Abstract

AbstractThe paper addresses detection of figurative usage of words in English text. The chosen method was to use neural nets fed by pretrained word embeddings. The obtained results show that simple solutions, based on words embeddings only, are comparable to complex solutions, using many sources of information which are not available for languages less-studied than English.

🐣 Hot Topic Early Bird - figurative language

Authors

Agnieszka Mykowiecka, Aleksander Wawer, Malgorzata Marciniak

Topics

Machine Learning > Core Methods > Classification Deep Learning > Architectures > Neural Networks

Keywords

natural language processing text classification recurrent neural network word embedding figurative language
Download PDF

More from NAACL 2018

All NAACL 2018 papers →
Neural Metaphor Detecting with CNN-LSTM Model
Di-LSTM Contrast : A Deep Neural Network for Metaphor Detection
Conditional Random Fields for Metaphor Detection
Multi-Module Recurrent Neural Networks with Transfer Learning
Using Language Learner Data for Metaphor Detection
Towards Inference-Oriented Reading Comprehension: ParallelQA