Deep Learning Methods for Extracting Metaphorical Names of Flowers and Plants

TL;DR

This paper explores deep learning techniques, including transformer models and ChatGPT, to automatically identify metaphorical flower and plant names in discourse, improving translation and lexicographic accuracy.

Contribution

It introduces a comparative analysis of transformer models and ChatGPT for metaphor detection in botany-related language, highlighting the superior performance of discriminative models.

Findings

Discriminative transformer models outperform GPT-3.5 in metaphor detection.

Best model achieves 92.23% F1 score in identifying metaphorical plant names.

Deep learning enhances accuracy in botanical metaphor recognition.

Abstract

The domain of Botany is rich with metaphorical terms. Those terms play an important role in the description and identification of flowers and plants. However, the identification of such terms in discourse is an arduous task. This leads in some cases to committing errors during translation processes and lexicographic tasks. The process is even more challenging when it comes to machine translation, both in the cases of single-word terms and multi-word terms. One of the recent concerns of Natural Language Processing (NLP) applications and Machine Translation (MT) technologies is the automatic identification of metaphor-based words in discourse through Deep Learning (DL). In this study, we seek to fill this gap through the use of thirteen popular transformer based models, as well as ChatGPT, and we show that discriminative models perform better than GPT-3.5 model with our best performer reporting 92.2349% F1 score in metaphoric flower and plant names identification task.