URJC-Team at HOPE2023@IberLEF: Multilingual Hope Speech Detection Using Transformers Architecture

Miguel Ángel Rodríguez-García; Adrián Riaño-Martínez; Soto Montalvo Herranz

URJC-Team at HOPE2023@IberLEF: Multilingual Hope Speech Detection Using Transformers Architecture

Miguel Ángel Rodríguez-García^*
, Adrián Riaño-Martínez
, Soto Montalvo Herranz

^*Corresponding author for this work

Universidad Rey Juan Carlos

Research output: Contribution to journal › Conference article › peer-review

Abstract

Detecting Hope Speech refers to identifying content in natural language that provokes optimism in people's minds, encouraging them to improve their life. This type of speech has a relevant target in our society, offering supporting messages for people suffering from depression, stress and loneliness. Despite its relevance, a significant number of published studies address to recognise the flip side of the coin, hate speech. This work describes our contribution to the HOPE challenge, i.e., detecting hope speech content in Spanish and English texts. Two different transform models are proposed to tackle the subtasks suggested in the challenge. Our proposal reaches notable results.

Original language	English
Journal	CEUR Workshop Proceedings
Volume	3496
Publication status	Published - 2023
Externally published	Yes
Event	2023 Iberian Languages Evaluation Forum, IberLEF 2023 - Jaen, Spain Duration: 26 Sept 2023 → …

Keywords

Deep Learning
Hope Speech
Natural Language Processing
Transformers

Cite this

@article{eac05bcb89374573a9e8d242d468d313,

title = "URJC-Team at HOPE2023@IberLEF: Multilingual Hope Speech Detection Using Transformers Architecture",

abstract = "Detecting Hope Speech refers to identifying content in natural language that provokes optimism in people's minds, encouraging them to improve their life. This type of speech has a relevant target in our society, offering supporting messages for people suffering from depression, stress and loneliness. Despite its relevance, a significant number of published studies address to recognise the flip side of the coin, hate speech. This work describes our contribution to the HOPE challenge, i.e., detecting hope speech content in Spanish and English texts. Two different transform models are proposed to tackle the subtasks suggested in the challenge. Our proposal reaches notable results.",

keywords = "Deep Learning, Hope Speech, Natural Language Processing, Transformers",

author = "Rodr{\'i}guez-Garc{\'i}a, \{Miguel {\'A}ngel\} and Adri{\'a}n Ria{\~n}o-Mart{\'i}nez and Herranz, \{Soto Montalvo\}",

note = "Publisher Copyright: {\textcopyright} 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).; 2023 Iberian Languages Evaluation Forum, IberLEF 2023 ; Conference date: 26-09-2023",

year = "2023",

language = "English",

volume = "3496",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

T1 - URJC-Team at HOPE2023@IberLEF

T2 - 2023 Iberian Languages Evaluation Forum, IberLEF 2023

AU - Rodríguez-García, Miguel Ángel

AU - Riaño-Martínez, Adrián

AU - Herranz, Soto Montalvo

PY - 2023

Y1 - 2023

N2 - Detecting Hope Speech refers to identifying content in natural language that provokes optimism in people's minds, encouraging them to improve their life. This type of speech has a relevant target in our society, offering supporting messages for people suffering from depression, stress and loneliness. Despite its relevance, a significant number of published studies address to recognise the flip side of the coin, hate speech. This work describes our contribution to the HOPE challenge, i.e., detecting hope speech content in Spanish and English texts. Two different transform models are proposed to tackle the subtasks suggested in the challenge. Our proposal reaches notable results.

AB - Detecting Hope Speech refers to identifying content in natural language that provokes optimism in people's minds, encouraging them to improve their life. This type of speech has a relevant target in our society, offering supporting messages for people suffering from depression, stress and loneliness. Despite its relevance, a significant number of published studies address to recognise the flip side of the coin, hate speech. This work describes our contribution to the HOPE challenge, i.e., detecting hope speech content in Spanish and English texts. Two different transform models are proposed to tackle the subtasks suggested in the challenge. Our proposal reaches notable results.

KW - Deep Learning

KW - Hope Speech

KW - Natural Language Processing

KW - Transformers

UR - https://www.scopus.com/pages/publications/85175298238

M3 - Conference article

AN - SCOPUS:85175298238

SN - 1613-0073

VL - 3496

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 26 September 2023

ER -

URJC-Team at HOPE2023@IberLEF: Multilingual Hope Speech Detection Using Transformers Architecture

Abstract

Keywords

Other files and links

Fingerprint

Cite this