| Title | Low Resource Style Transfer via Domain Adaptive Meta Learning |
| Authors | Li, Xiangyang Long, Xiang Xia, Yu Li, Sujian |
| Affiliation | Peking Univ, Key Lab Computat Linguist, MOE, Beijing, Peoples R China Beijing Univ Posts & Telecommun, Beijing, Peoples R China |
| Issue Date | 2022 |
| Publisher | NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES |
| Abstract | Text style transfer (TST) without parallel data has achieved some practical success. However, most of the existing unsupervised text style transfer methods suffer from (i) requiring massive amounts of non-parallel data to guide transferring different text styles. (ii) colossal performance degradation when fine-tuning the model in new domains. In this work, we propose DAML-ATM (Domain Adaptive Meta-Learning with Adversarial Transfer Model), which consists of two parts: DAML and ATM. DAML is a domain adaptive meta-learning approach to learn general knowledge in multiple heterogeneous source domains, capable of adapting to new unseen domains with a small amount of data. Moreover, we propose a new unsupervised TST approach Adversarial Transfer Model (ATM), composed of a sequence-to-sequence pre-trained language model and uses adversarial style training for better content preservation and style transfer. Results on multi-domain datasets demonstrate that our approach generalizes well on unseen low-resource domains, achieving state-of-the-art results against ten strong baselines. |
| URI | http://hdl.handle.net/20.500.11897/657179 |
| ISBN | 978-1-955917-71-1 |
| DOI | 10.48550/arXiv.2205.12475 |
| Indexed | EI CPCI-SSH(ISSHP) CPCI-S(ISTP) |
| Appears in Collections: | 计算语言学教育部重点实验室 |
