NAACL 2021long24 citations

Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection

Xu Guo, Boyang Li, Han Yu, Chunyan Miao

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.

BibTeX
@inproceedings{guo-etal-2021-latent,
    title = "Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection",
    author = "Guo, Xu  and
      Li, Boyang  and
      Yu, Han  and
      Miao, Chunyan",
    editor = "Toutanova, Kristina  and
      Rumshisky, Anna  and
      Zettlemoyer, Luke  and
      Hakkani-Tur, Dilek  and
      Beltagy, Iz  and
      Bethard, Steven  and
      Cotterell, Ryan  and
      Chakraborty, Tanmoy  and
      Zhou, Yichao",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.naacl-main.425/",
    doi = "10.18653/v1/2021.naacl-main.425",
    pages = "5394--5407"
}
Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection · NAACL 2021