Aspect-Based Sentiment Analysis (ABSA) studies 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 fine-tune the general purpose BERT and domain specific post-trained BERT (BERT-PT) using adversarial training. After improving the results of post-trained BERT with different hyperparameters, we propose a novel architecture called BERT Adversarial Training (BAT) to utilize adversarial training for the two major tasks of Aspect Extraction and Aspect Sentiment Classification in sentiment analysis. The proposed model outperforms the general BERT as well as the in-domain 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.

Adversarial training for aspect-based sentiment analysis with BERT / Karimi, A.; Rossi, L.; Prati, A.. - (2020), pp. 9412167.8797-9412167.8803. ((Intervento presentato al convegno 25th International Conference on Pattern Recognition, ICPR 2020 tenutosi a ita nel 2021 [10.1109/ICPR48806.2021.9412167].

Adversarial training for aspect-based sentiment analysis with BERT

Karimi A.
Methodology
;
Rossi L.
Writing – Review & Editing
;
Prati A.
Supervision
2020

Abstract

Aspect-Based Sentiment Analysis (ABSA) studies 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 fine-tune the general purpose BERT and domain specific post-trained BERT (BERT-PT) using adversarial training. After improving the results of post-trained BERT with different hyperparameters, we propose a novel architecture called BERT Adversarial Training (BAT) to utilize adversarial training for the two major tasks of Aspect Extraction and Aspect Sentiment Classification in sentiment analysis. The proposed model outperforms the general BERT as well as the in-domain 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.
978-1-7281-8808-9
Adversarial training for aspect-based sentiment analysis with BERT / Karimi, A.; Rossi, L.; Prati, A.. - (2020), pp. 9412167.8797-9412167.8803. ((Intervento presentato al convegno 25th International Conference on Pattern Recognition, ICPR 2020 tenutosi a ita nel 2021 [10.1109/ICPR48806.2021.9412167].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11381/2896670
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 21
  • ???jsp.display-item.citation.isi??? 15
social impact