Neural Metaphor Detection with a Residual biLSTM-CRF Model

Andrés Torres Rivera, Antoni Oliver, Salvador Climent, Marta Coll-Florit


Abstract
In this paper we present a novel resource-inexpensive architecture for metaphor detection based on a residual bidirectional long short-term memory and conditional random fields. Current approaches on this task rely on deep neural networks to identify metaphorical words, using additional linguistic features or word embeddings. We evaluate our proposed approach using different model configurations that combine embeddings, part of speech tags, and semantically disambiguated synonym sets. This evaluation process was performed using the training and testing partitions of the VU Amsterdam Metaphor Corpus. We use this method of evaluation as reference to compare the results with other current neural approaches for this task that implement similar neural architectures and features, and that were evaluated using this corpus. Results show that our system achieves competitive results with a simpler architecture compared to previous approaches.
Anthology ID:
2020.figlang-1.27
Volume:
Proceedings of the Second Workshop on Figurative Language Processing
Month:
July
Year:
2020
Address:
Online
Venues:
ACL | Fig-Lang | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
197–203
Language:
URL:
https://www.aclweb.org/anthology/2020.figlang-1.27
DOI:
10.18653/v1/2020.figlang-1.27
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.figlang-1.27.pdf
Video:
 http://slideslive.com/38929722