Deep Learning Brasil at ABSAPT 2022: Portuguese Transformer Ensemble Approaches

Juliana Resplande Santanna Gomes, Eduardo Augusto Santos Garcia, Adalberto Ferreira Barbosa Junior, Ruan Chaves Rodrigues, Diogo Fernandes Costa Silva +4 more
11/8/2023
cs.CL

No official code found. Best implementation: ju-resplande/dlb_absapt2022 (4 stars, CC-BY-4.0, last commit 2025-08-18).

Abstract

Aspect-based Sentiment Analysis (ABSA) is a task whose objective is to classify the individual sentiment polarity of all entities, called aspects, in a sentence. The task is composed of two subtasks: Aspect Term Extraction (ATE), identify all aspect terms in a sentence; and Sentiment Orientation Extraction (SOE), given a sentence and its aspect terms, the task is to determine the sentiment polarity of each aspect term (positive, negative or neutral). This article presents we present our participation in Aspect-Based Sentiment Analysis in Portuguese (ABSAPT) 2022 at IberLEF 2022. We submitted the best performing systems, achieving new state-of-the-art results on both subtasks.

View on arXivView PDF

Code Implementations(1)

ju-resplande/dlb_absapt2022Community100%
CC-BY-4.0

DLB at ABSAPT 2022.

40Shell, PythonMay 6, 20221 years agoCC-BY-4.0
natural-language-processingnlpportuguesesentiment-analysissentiment-polarity+1 more

Similar Papers

EDSA-Ensemble: an Event Detection Sentiment Analysis Ensemble Architecture

86% match2023

USA: Universal Sentiment Analysis Model & Construction of Japanese Sentiment Text Classification and Part of Speech Dataset

85% match2023

ATESA-BÆRT: A Heterogeneous Ensemble Learning Model for Aspect-Based Sentiment Analysis

84% match2023

SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis (DimABSA)

84% match2026

Aspect-Based Sentiment Analysis using Local Context Focus Mechanism with DeBERTa

84% match2022

ATP: A holistic attention integrated approach to enhance ABSA

83% match2022

Cite this paper

@article{gomes2023deep,
  title  = {Deep Learning Brasil at ABSAPT 2022: Portuguese Transformer Ensemble Approaches},
  author = {Juliana Resplande Santanna Gomes and Eduardo Augusto Santos Garcia and Adalberto Ferreira Barbosa Junior and Ruan Chaves Rodrigues and Diogo Fernandes Costa Silva and Dyonnatan Ferreira Maia and Nádia Félix Felipe da Silva and Arlindo Rodrigues Galvão Filho and Anderson da Silva Soares},
  year   = {2023},
  eprint = {2311.05051},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.05051v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.05051.svg)](https://codeofpaper.com/paper/2311.05051)

Discussion