Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles
Eric Michael Smith, Diana Gonzalez-Rico, Emily Dinan, Y-Lan Boureau Facebook AI Research
Abstract
Text style transfer is usually performed using attributes that can take a handful of discrete values (e.g., positive to negative reviews). In this work, we introduce an architecture that can leverage pre-trained consistent continuous distributed style representations and use them to transfer to an attribute unseen during training, without requiring any re-tuning of the style transfer model. We demonstrate the method by training an architecture to transfer text conveying one sentiment to another sentiment, using a fine-grained set of over 20 sentiment labels rather than the binary positive/negative often used in style transfer. Our experiments show that this model can then rewrite text to match a target sentiment that was unseen during training.
中文速览
现有文本风格迁移方法通常只能在少数几个离散标签（如"正面/负面"情感）之间切换，无法迁移到训练时从未见过的新风格。研究者提出了一种新架构，核心思路是把目标风格不再表示为查表的独热向量，而是用预训练分类器输出的低维连续分布式嵌入（distributed embedding）来编码，再通过一个可学习的线性变换对接到原有的序列到序列风格迁移框架中。他们以细粒度情感迁移为实验场景，用超过20种情感标签（如高兴、愤怒、悲伤、感激等）训练模型，结果显示该模型不仅能在这些细粒度标签间完成高质量风格迁移，还能对训练期间完全未见过的目标情感实现零样本（zero-shot）迁移，而无需对风格迁移模型进行任何重新调优。这项工作的重要性在于，它将风格迁移从"有限离散类别之间的切换"扩展为"在连续嵌入空间中自由指定目标风格"，为更丰富、更灵活的可控文本生成打开了新的可能。
原文 arXiv:1911.03914;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1911.03914v1