Home > Research > Publications & Outputs > Transformer-based Detection of Multiword Expres...

Research

Electronic data

  • 2209.08016v2

    Final published version, 288 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Keywords

View graph of relations

Transformer-based Detection of Multiword Expressions in Flower and Plant Names

Research output: Working paper › Preprint

Published

Standard

Transformer-based Detection of Multiword Expressions in Flower and Plant Names. / Premasiri, Damith; Haddad, Amal Haddad; Ranasinghe, Tharindu et al.
Arxiv, 2022.

Research output: Working paper › Preprint

Harvard

Premasiri, D, Haddad, AH, Ranasinghe, T & Mitkov, R 2022 'Transformer-based Detection of Multiword Expressions in Flower and Plant Names' Arxiv. <https://arxiv.org/abs/2209.08016v2>

APA

Premasiri, D., Haddad, A. H., Ranasinghe, T., & Mitkov, R. (2022). Transformer-based Detection of Multiword Expressions in Flower and Plant Names. Arxiv. https://arxiv.org/abs/2209.08016v2

Vancouver

Premasiri D, Haddad AH, Ranasinghe T, Mitkov R. Transformer-based Detection of Multiword Expressions in Flower and Plant Names. Arxiv. 2022 Sept 20. Epub 2022 Sept 16.

Author

Premasiri, Damith ; Haddad, Amal Haddad ; Ranasinghe, Tharindu et al. / Transformer-based Detection of Multiword Expressions in Flower and Plant Names. Arxiv, 2022.

Bibtex

@techreport{af04cabcf9c14520823fc9737569b9ac,
title = "Transformer-based Detection of Multiword Expressions in Flower and Plant Names",
abstract = "Multiword expression (MWE) is a sequence of words which collectively present a meaning which is not derived from its individual words. The task of processing MWEs is crucial in many natural language processing (NLP) applications, including machine translation and terminology extraction. Therefore, detecting MWEs in different domains is an important research topic. In this paper, we explore state-of-the-art neural transformers in the task of detecting MWEs in flower and plant names. We evaluate different transformer models on a dataset created from Encyclopedia of Plants and Flower. We empirically show that transformer models outperform the previous neural models based on long short-term memory (LSTM). ",
keywords = "cs.CL",
author = "Damith Premasiri and Haddad, {Amal Haddad} and Tharindu Ranasinghe and Ruslan Mitkov",
note = "Submitted to The 5th Workshop on Multi-word Units in Machine Translation and Translation Technology at Europhras2022",
year = "2022",
month = sep,
day = "20",
language = "English",
publisher = "Arxiv",
type = "WorkingPaper",
institution = "Arxiv",

}

RIS

TY - UNPB

T1 - Transformer-based Detection of Multiword Expressions in Flower and Plant Names

AU - Premasiri, Damith

AU - Haddad, Amal Haddad

AU - Ranasinghe, Tharindu

AU - Mitkov, Ruslan

N1 - Submitted to The 5th Workshop on Multi-word Units in Machine Translation and Translation Technology at Europhras2022

PY - 2022/9/20

Y1 - 2022/9/20

N2 - Multiword expression (MWE) is a sequence of words which collectively present a meaning which is not derived from its individual words. The task of processing MWEs is crucial in many natural language processing (NLP) applications, including machine translation and terminology extraction. Therefore, detecting MWEs in different domains is an important research topic. In this paper, we explore state-of-the-art neural transformers in the task of detecting MWEs in flower and plant names. We evaluate different transformer models on a dataset created from Encyclopedia of Plants and Flower. We empirically show that transformer models outperform the previous neural models based on long short-term memory (LSTM).

AB - Multiword expression (MWE) is a sequence of words which collectively present a meaning which is not derived from its individual words. The task of processing MWEs is crucial in many natural language processing (NLP) applications, including machine translation and terminology extraction. Therefore, detecting MWEs in different domains is an important research topic. In this paper, we explore state-of-the-art neural transformers in the task of detecting MWEs in flower and plant names. We evaluate different transformer models on a dataset created from Encyclopedia of Plants and Flower. We empirically show that transformer models outperform the previous neural models based on long short-term memory (LSTM).

KW - cs.CL

M3 - Preprint

BT - Transformer-based Detection of Multiword Expressions in Flower and Plant Names

PB - Arxiv

ER -