Abstract
We present a simple, but effective method to incorporate syntactic dependency information directly into transformer-based language models (e.g. RoBERTa) for tasks such as Aspect-Based Sentiment Classification (ABSC), where the desired output depends on specific input tokens. In contrast to prior approaches to ABSC that capture syntax by combining language models with graph neural networks over dependency trees, our model, Syntax-Integrated RoBERTa for ABSC (SIR-ABSC) incorporates syntax directly into the language model by using a novel aggregator token. Yet, SIR-ABSC outperforms these more complex models, yielding new state-of-the-art results on ABSC.- Anthology ID:
- 2023.findings-emnlp.572
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8535–8550
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.572
- DOI:
- 10.18653/v1/2023.findings-emnlp.572
- Cite (ACL):
- Ikhyun Cho, Yoonhwa Jung, and Julia Hockenmaier. 2023. SIR-ABSC: Incorporating Syntax into RoBERTa-based Sentiment Analysis Models with a Special Aggregator Token. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8535–8550, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- SIR-ABSC: Incorporating Syntax into RoBERTa-based Sentiment Analysis Models with a Special Aggregator Token (Cho et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.findings-emnlp.572.pdf