Urjc-team at emoevales 2021: Bert for emotion classification in spanish tweets

Jorge Alberto Flores Sánchez; Soto Montalvo Herranz; Raquel Martínez Unanue

doi:100000/000

Urjc-team at emoevales 2021: Bert for emotion classification in spanish tweets

Jorge Alberto Flores Sánchez
, Soto Montalvo Herranz
, Raquel Martínez Unanue

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

2 Citations (Scopus)

Abstract

This paper describes the participation of the URJC-Team in the EmoEvalEs 2021 task of the IberLEF evaluation campaign. The task consists of classifying the emotion expressed in a tweet among seven different classes of emotion. Our proposal is based on transfer learning using BERT language modeling. We train three fine-tuned BERT models finally selecting for the submitted runs two of them, along with a system that combines all the models by means of an ensemble method. We obtained competitive results in the challenge, ranking fifth. Additional work needs to be done to improve the results.

Original language	English
Pages (from-to)	43-48
Number of pages	6
Journal	CEUR Workshop Proceedings
Volume	2943
DOIs	https://doi.org/100000/000
Publication status	Published - 2021
Externally published	Yes
Event	2021 Iberian Languages Evaluation Forum, IberLEF 2021 - Virtual, Malaga, Spain Duration: 21 Sept 2021 → …

Keywords

Deep Learning
Emotion Classification
Transformer
Tweets

Access to Document

100000/000

Cite this

@article{ea7038c99c014ac29cad4b2a0c1fa7bf,

title = "Urjc-team at emoevales 2021: Bert for emotion classification in spanish tweets",

abstract = "This paper describes the participation of the URJC-Team in the EmoEvalEs 2021 task of the IberLEF evaluation campaign. The task consists of classifying the emotion expressed in a tweet among seven different classes of emotion. Our proposal is based on transfer learning using BERT language modeling. We train three fine-tuned BERT models finally selecting for the submitted runs two of them, along with a system that combines all the models by means of an ensemble method. We obtained competitive results in the challenge, ranking fifth. Additional work needs to be done to improve the results.",

keywords = "Deep Learning, Emotion Classification, Transformer, Tweets",

author = "S{\'a}nchez, \{Jorge Alberto Flores\} and Herranz, \{Soto Montalvo\} and Unanue, \{Raquel Mart{\'i}nez\}",

year = "2021",

doi = "100000/000",

language = "English",

volume = "2943",

pages = "43--48",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

T1 - Urjc-team at emoevales 2021

T2 - 2021 Iberian Languages Evaluation Forum, IberLEF 2021

AU - Sánchez, Jorge Alberto Flores

AU - Herranz, Soto Montalvo

AU - Unanue, Raquel Martínez

PY - 2021

Y1 - 2021

N2 - This paper describes the participation of the URJC-Team in the EmoEvalEs 2021 task of the IberLEF evaluation campaign. The task consists of classifying the emotion expressed in a tweet among seven different classes of emotion. Our proposal is based on transfer learning using BERT language modeling. We train three fine-tuned BERT models finally selecting for the submitted runs two of them, along with a system that combines all the models by means of an ensemble method. We obtained competitive results in the challenge, ranking fifth. Additional work needs to be done to improve the results.

AB - This paper describes the participation of the URJC-Team in the EmoEvalEs 2021 task of the IberLEF evaluation campaign. The task consists of classifying the emotion expressed in a tweet among seven different classes of emotion. Our proposal is based on transfer learning using BERT language modeling. We train three fine-tuned BERT models finally selecting for the submitted runs two of them, along with a system that combines all the models by means of an ensemble method. We obtained competitive results in the challenge, ranking fifth. Additional work needs to be done to improve the results.

KW - Deep Learning

KW - Emotion Classification

KW - Transformer

KW - Tweets

UR - https://www.scopus.com/pages/publications/85115315898

U2 - 100000/000

DO - 100000/000

M3 - Conference article

AN - SCOPUS:85115315898

SN - 1613-0073

VL - 2943

SP - 43

EP - 48

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 21 September 2021

ER -

Urjc-team at emoevales 2021: Bert for emotion classification in spanish tweets

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this