Papers › Adversarial Training for Aspect-Based Sentiment Analysis with BERT
Adversarial Training for Aspect-Based Sentiment Analysis with BERT
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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