Abstract
The existence of multiple datasets for sarcasm detection prompts us to apply transfer learning to exploit their commonality. The adversarial neural transfer (ANT) framework utilizes multiple loss terms that encourage the source-domain and the target-domain feature distributions to be similar while optimizing for domain-specific performance. However, these objectives may be in conflict, which can lead to optimization difficulties and sometimes diminished transfer. We propose a generalized latent optimization strategy that allows different losses to accommodate each other and improves training dynamics. The proposed method outperforms transfer learning and meta-learning baselines. In particular, we achieve 10.02% absolute performance gain over the previous state of the art on the iSarcasm dataset.- Anthology ID:
- 2021.naacl-main.425
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Editors:
- Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5394–5407
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.425
- DOI:
- 10.18653/v1/2021.naacl-main.425
- Cite (ACL):
- Xu Guo, Boyang Li, Han Yu, and Chunyan Miao. 2021. Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5394–5407, Online. Association for Computational Linguistics.
- Cite (Informal):
- Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection (Guo et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2021.naacl-main.425.pdf
- Code
- guoxuxu/LOANT
- Data
- iSarcasm