Testing the role of metadata in metaphor identification

Egon Stemle, Alexander Onysko


Abstract
This paper describes the adaptation and application of a neural network system for the automatic detection of metaphors. The LSTM BiRNN system participated in the shared task of metaphor identification that was part of the Second Workshop of Figurative Language Processing (FigLang2020) held at the Annual Conference of the Association for Computational Linguistics (ACL2020). The particular focus of our approach is on the potential influence that the metadata given in the ETS Corpus of Non-Native Written English might have on the automatic detection of metaphors in this dataset. The article first discusses the annotated ETS learner data, highlighting some of its peculiarities and inherent biases of metaphor use. A series of evaluations follow in order to test whether specific metadata influence the system performance in the task of automatic metaphor identification. The system is available under the APLv2 open-source license.
Anthology ID:
2020.figlang-1.35
Volume:
Proceedings of the Second Workshop on Figurative Language Processing
Month:
July
Year:
2020
Address:
Online
Venue:
Fig-Lang
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
256–263
Language:
URL:
https://aclanthology.org/2020.figlang-1.35
DOI:
10.18653/v1/2020.figlang-1.35
Bibkey:
Cite (ACL):
Egon Stemle and Alexander Onysko. 2020. Testing the role of metadata in metaphor identification. In Proceedings of the Second Workshop on Figurative Language Processing, pages 256–263, Online. Association for Computational Linguistics.
Cite (Informal):
Testing the role of metadata in metaphor identification (Stemle & Onysko, Fig-Lang 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.figlang-1.35.pdf
Video:
 http://slideslive.com/38929730