Low Resource Style Transfer via Domain Adaptive Meta Learning

Anonymous

Paper Link: https://openreview.net/forum?id=p_-ZgMkRD3

Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)

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.

Presentation Mode: This paper will be presented virtually

Copyright Consent Signature (type Name Or NA If Not Transferrable): Xiangyang Li

Copyright Consent Name And Address: Peking University, 5 Yiheyuan Road Haidian District Beijing PRC 100871