Papers › Adversarial Training for Aspect-Based Sentiment Analysis with BERT

Adversarial Training for Aspect-Based Sentiment Analysis with BERT

30 Jan 2020arXiv:2001.11316archive 2025-07-28

Akbar Karimi, Leonardo Rossi, Andrea Prati

Aspect-Based Sentiment Analysis (ABSA) deals with the extraction of sentiments and their targets. Collecting labeled data for this task in order to help neural networks generalize better can be laborious and time-consuming. As an alternative, similar data to the real-world examples can be produced artificially through an adversarial process which is carried out in the embedding space. Although these examples are not real sentences, they have been shown to act as a regularization method which can make neural networks more robust. In this work, we apply adversarial training, which was put forward by Goodfellow et al. (2014), to the post-trained BERT (BERT-PT) language model proposed by Xu et al. (2019) on the two major tasks of Aspect Extraction and Aspect Sentiment Classification in sentiment analysis. After improving the results of post-trained BERT by an ablation study, we propose a novel architecture called BERT Adversarial Training (BAT) to utilize adversarial training in ABSA. The proposed model outperforms post-trained BERT in both tasks. To the best of our knowledge, this is the first study on the application of adversarial training in ABSA.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

IMPLabUniPr/Adversarial-Training-for-ABSA officialmentioned in papermentioned on GitHubpytorch report
IMPLabUniPr/BERT-for-ABSA mentioned on GitHubpytorchApache-2.0 report
akkarimi/Adversarial-Training-for-ABSA mentioned on GitHubpytorchApache-2.0 report
leanhkhoi/AE_BERT_CROSS_SENTENCES mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Aspect ExtractionAspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Language ModelingLanguage ModellingSentiment AnalysisSentiment Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Aspect Extraction SemEval-2014 Task-4 BAT Laptop (F1) 85.57 #4 of 6 Archive leaderboard report
Aspect Extraction SemEval-2014 Task-4 BAT Mean F1 (Laptop + Restaurant) 83.54 #4 of 6 Archive leaderboard report
Aspect Extraction SemEval-2014 Task-4 BAT Restaurant (F1) 81.50 #4 of 6 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 BAT Laptop (Acc) 79.35 #13 of 48 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 BAT Mean Acc (Restaurant + Laptop) 82.69 #13 of 48 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) SemEval-2014 Task-4 BAT Restaurant (Acc) 86.03 #13 of 48 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections