Exploiting BERT to improve aspect-based sentiment analysis performance on Persian language

• URL: http://arxiv.org/abs/2012.07510v1
• Date: Wed, 2 Dec 2020 16:47:20 GMT
• Title: Exploiting BERT to improve aspect-based sentiment analysis performance on Persian language
• Authors: H. Jafarian, A. H. Taghavi, A. Javaheri and R. Rawassizadeh
• Abstract summary: This research shows the potential of using pre-trained BERT model and taking advantage of using sentence-pair input on an ABSA task. The results indicate that employing Pars-BERT pre-trained model along with natural language inference auxiliary sentence (NLI-M) could boost the ABSA task accuracy up to 91%.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Aspect-based sentiment analysis (ABSA) is a more detailed task in sentiment analysis, by identifying opinion polarity toward a certain aspect in a text. This method is attracting more attention from the community, due to the fact that it provides more thorough and useful information. However, there are few language-specific researches on Persian language. The present research aims to improve the ABSA on the Persian Pars-ABSA dataset. This research shows the potential of using pre-trained BERT model and taking advantage of using sentence-pair input on an ABSA task. The results indicate that employing Pars-BERT pre-trained model along with natural language inference auxiliary sentence (NLI-M) could boost the ABSA task accuracy up to 91% which is 5.5% (absolute) higher than state-of-the-art studies on Pars-ABSA dataset.

Related papers

• Iterative Data Augmentation with Large Language Models for Aspect-based Sentiment Analysis [82.98490089763175]
  Aspect-based Sentiment Analysis (ABSA) is an important sentiment analysis task, which aims to determine the sentiment polarity towards an aspect in a sentence. Due to the expensive and limited labeled data, data augmentation (DA) has become the standard for improving the performance of ABSA. We propose a systematic Iterative Data augmentation framework, namely IterD, to boost the performance of ABSA.
  arXiv  Detail & Related papers  (2024-06-29T07:00:37Z)
• ROAST: Review-level Opinion Aspect Sentiment Target Joint Detection for ABSA [50.90538760832107]
  This research presents a novel task, Review-Level Opinion Aspect Sentiment Target (ROAST) ROAST seeks to close the gap between sentence-level and text-level ABSA by identifying every ABSA constituent at the review level. We extend the available datasets to enable ROAST, addressing the drawbacks noted in previous research.
  arXiv  Detail & Related papers  (2024-05-30T17:29:15Z)
• SOUL: Towards Sentiment and Opinion Understanding of Language [96.74878032417054]
  We propose a new task called Sentiment and Opinion Understanding of Language (SOUL) SOUL aims to evaluate sentiment understanding through two subtasks: Review (RC) and Justification Generation (JG)
  arXiv  Detail & Related papers  (2023-10-27T06:48:48Z)
• Survey of Aspect-based Sentiment Analysis Datasets [55.61047894397937]
  Aspect-based sentiment analysis (ABSA) is a natural language processing problem that requires analyzing user-generated reviews. Numerous yet scattered corpora for ABSA make it difficult for researchers to identify corpora best suited for a specific ABSA subtask quickly. This study aims to present a database of corpora that can be used to train and assess autonomous ABSA systems.
  arXiv  Detail & Related papers  (2022-04-11T16:23:36Z)
• CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment Analysis [4.60495447017298]
  We propose a novel framework, CL-XABSA: Contrastive Learning for Cross-lingual Aspect-Based Sentiment Analysis. Specifically, we design two contrastive strategies, token level contrastive learning of token embeddings (TL-CTE) and sentiment level contrastive learning of token embeddings (SL-CTE) Since our framework can receive datasets in multiple languages during training, our framework can be adapted not only for XABSA task, but also for multilingual aspect-based sentiment analysis (MABSA)
  arXiv  Detail & Related papers  (2022-04-02T07:40:03Z)
• Arabic aspect based sentiment analysis using BERT [0.0]
  This article explores the modeling capabilities of contextual embeddings from pre-trained language models, such as BERT. We are building a simple but effective BERT-based neural baseline to handle this task. Our BERT architecture with a simple linear classification layer surpassed the state-of-the-art works, according to the experimental results.
  arXiv  Detail & Related papers  (2021-07-28T11:34:00Z)
• Fine-tuning Pretrained Multilingual BERT Model for Indonesian Aspect-based Sentiment Analysis [0.0]
  Previous research on Aspect-based Sentiment Analysis (ABSA) for Indonesian reviews in hotel domain has been conducted using CNN and XGBoost. In this paper, we intend to incorporate one of the foremost language representation model, BERT, to perform ABSA in Indonesian reviews dataset.
  arXiv  Detail & Related papers  (2021-03-05T15:05:51Z)
• Understanding Pre-trained BERT for Aspect-based Sentiment Analysis [71.40586258509394]
  This paper analyzes the pre-trained hidden representations learned from reviews on BERT for tasks in aspect-based sentiment analysis (ABSA) It is not clear how the general proxy task of (masked) language model trained on unlabeled corpus without annotations of aspects or opinions can provide important features for downstream tasks in ABSA.
  arXiv  Detail & Related papers  (2020-10-31T02:21:43Z)
• Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis [71.40390724765903]
  Aspect-based sentiment analysis (ABSA) aims to predict the sentiment towards a specific aspect in the text. Existing ABSA test sets cannot be used to probe whether a model can distinguish the sentiment of the target aspect from the non-target aspects. We generate new examples to disentangle the confounding sentiments of the non-target aspects from the target aspect's sentiment.
  arXiv  Detail & Related papers  (2020-09-16T22:38:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.