Towards Generative Aspect-Based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) has received increasing attention recently. Most existing work tackles ABSA in a discriminative manner, designing various task-specific classification networks for the prediction. Despite their effectiveness, these methods ignore the rich label semantics in ABSA problems and require extensive task-specific designs. In this paper, we propose to tackle various ABSA tasks in a unified generative framework. Two types of paradigms, namely annotation-style and extraction-style modeling, are designed to enable the training process by formulating each ABSA task as a text generation problem. We conduct experiments on four ABSA tasks across multiple benchmark datasets where our proposed generative approach achieves new state-of-the-art results in almost all cases. This also validates the strong generality of the proposed framework which can be easily adapted to arbitrary ABSA task without additional taskspecific model design.
PDF Abstract ACL 2021 PDF ACL 2021 AbstractDatasets
Results from the Paper
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Aspect-Based Sentiment Analysis (ABSA) | ASQP | GAS | F1 (R15) | 45.98 | # 7 | |
F1 (R16) | 56.03 | # 7 | ||||
Aspect-Based Sentiment Analysis (ABSA) | ASTE | GAS | F1 (L14) | 58.19 | # 9 | |
F1(R14) | 70.52 | # 9 | ||||
F1 (R15) | 60.23 | # 9 | ||||
F1 (R16) | 69.05 | # 9 | ||||
Aspect Sentiment Triplet Extraction | ASTE-Data-V2 | GAS | F1 | 72.16 | # 4 | |
Aspect-Based Sentiment Analysis (ABSA) | TASD | GAS | F1 (R15) | 60.63 | # 6 | |
F1 (R16) | 68.31 | # 6 |