An Effective Contextual Language Ensemble Model for Vietnamese Aspect-based Sentiment Analysis

Thin, Dang Van; Hao, Duong Ngoc; Nguyen, Ngan Luu-Thuy

doi:10.1109/nics56915.2022.10013429

Cited by 2 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concretely, the T5 architecture achieved a performance of 75.53% in terms of the F1-score, which is higher than the state-of-the-art score of an ensemble of different BERT models [25], but the difference is not significant. However, it can be observed that our model relies less on computational complexity than the ensemble BERT model.…”

Section: Resultsmentioning

confidence: 84%

Aspect-Category based Sentiment Analysis with Unified Sequence-To-Sequence Transfer Transformers

Thin¹,

Nguyen²

2023

JCSCE

View full text Add to dashboard Cite

In recent years, Aspect-based sentiment analysis (ABSA) has received increasing attention from the scientific community for Vietnamese language. However, most previous studies solved various subtasks in ABSA based on machine learning, deep learning and transformer-based architectures in a classification way. Recently, the release of pre-trained sequence-to-sequence brings a new approach to address the ABSA as a text generation problem for Vietnamese ABSA tasks. In this paper, we formulate the Aspect-category based sentiment analysis task as the conditional text generation task and investigate different unified generative transformer-based models. To represent the labels in a natural sentence, we apply a simple statistical method and observation of the commenting style. We conduct experiments on two benchmark datasets. As a result, our model achieved new state-of-the-art results with the micro F1-score of 75.53% and 86.60% for the two datasets with different levels for the restaurant domain. In addition, our experimental results achieved the best score for the smartphone domain with the macro F1-score of 81.10%.

show abstract

Section: Resultsmentioning

confidence: 84%

Aspect-Category based Sentiment Analysis with Unified Sequence-To-Sequence Transfer Transformers

Thin¹,

Nguyen²

2023

JCSCE

View full text Add to dashboard Cite

show abstract

A Systematic Literature Review on Vietnamese Aspect-based Sentiment Analysis

Thin

Hao

Nguyen

2023

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

View full text Add to dashboard Cite

Aspect-based sentiment analysis (ABSA) is one of the principal tasks in the automatic deep understanding of texts, widely applied in a broad range of real-world applications. Many studies have been performed on different tasks and datasets for other languages (e.g., English, Chinese, etc.) to address this topic. For Vietnamese language, this topic has been attracting considerable interest in recent years. However, we found that many studies tend to repeat the research instead of inheriting and extending the previous works. Moreover, previous studies’ methods of comparison or evaluation metrics have not shown consistency and connection. This might restrict the development of future studies on this research topic. To the best of our knowledge, no research has been conducted to overview the existing studies for the ABSA research in Vietnamese language. The primary objective of this study is to provide a systematic and comprehensive review of the current Vietnamese ABSA research. More specifically, we analyze the early approaches, evaluation metrics, and available published benchmark datasets used in the Vietnamese ABSA task. We also discuss the challenge and recommend potential future directions for Vietnamese ABSA. This work is expected to provide readers with a wealth of knowledge, the research gap and the challenges in the Vietnamese ABSA field.

show abstract

An Effective Contextual Language Ensemble Model for Vietnamese Aspect-based Sentiment Analysis

Cited by 2 publications

References 22 publications

Aspect-Category based Sentiment Analysis with Unified Sequence-To-Sequence Transfer Transformers

Aspect-Category based Sentiment Analysis with Unified Sequence-To-Sequence Transfer Transformers

A Systematic Literature Review on Vietnamese Aspect-based Sentiment Analysis

Contact Info

Product

Resources

About