Home > Research > Publications & Outputs > Deep Learning Methods for Extracting Metaphoric...

Research

Associated organisational units

Electronic data

View graph of relations

Deep Learning Methods for Extracting Metaphorical Names of Flowers and Plants

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Forthcoming

Standard

Deep Learning Methods for Extracting Metaphorical Names of Flowers and Plants. / Mitkov, Ruslan; Haddad Haddad, Amal; Dola Mullage, Damith et al.
In: Procesamiento del Lenguaje Natural, Vol. 71, 17.05.2023.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Mitkov, R, Haddad Haddad, A, Dola Mullage, D & Ranasinghe, T 2023, 'Deep Learning Methods for Extracting Metaphorical Names of Flowers and Plants', Procesamiento del Lenguaje Natural, vol. 71.

APA

Mitkov, R., Haddad Haddad, A., Dola Mullage, D., & Ranasinghe, T. (in press). Deep Learning Methods for Extracting Metaphorical Names of Flowers and Plants. Procesamiento del Lenguaje Natural, 71.

Vancouver

Mitkov R, Haddad Haddad A, Dola Mullage D, Ranasinghe T. Deep Learning Methods for Extracting Metaphorical Names of Flowers and Plants. Procesamiento del Lenguaje Natural. 2023 May 17;71.

Author

Mitkov, Ruslan ; Haddad Haddad, Amal ; Dola Mullage, Damith et al. / Deep Learning Methods for Extracting Metaphorical Names of Flowers and Plants. In: Procesamiento del Lenguaje Natural. 2023 ; Vol. 71.

Bibtex

@article{53689387d78b4273b0d7badb1e9ef596,
title = "Deep Learning Methods for Extracting Metaphorical Names of Flowers and Plants",
abstract = "The domain of Botany is rich with metaphoical terms. Those termsplay 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.",
author = "Ruslan Mitkov and {Haddad Haddad}, Amal and {Dola Mullage}, Damith and Tharindu Ranasinghe",
year = "2023",
month = may,
day = "17",
language = "English",
volume = "71",
journal = "Procesamiento del Lenguaje Natural",

}

RIS

TY - JOUR

T1 - Deep Learning Methods for Extracting Metaphorical Names of Flowers and Plants

AU - Mitkov, Ruslan

AU - Haddad Haddad, Amal

AU - Dola Mullage, Damith

AU - Ranasinghe, Tharindu

PY - 2023/5/17

Y1 - 2023/5/17

N2 - The domain of Botany is rich with metaphoical terms. Those termsplay 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.

AB - The domain of Botany is rich with metaphoical terms. Those termsplay 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.

M3 - Journal article

VL - 71

JO - Procesamiento del Lenguaje Natural

JF - Procesamiento del Lenguaje Natural

ER -