Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While this has been well investigated in Computer Vision, in tasks such as image disentanglement, in the NLP domain sentence disentanglement is still comparatively under-investigated. Most previous work have concentrated on disentangling task-specific generative factors, such as sentiment, within the context of style transfer. In this work, we focus on a more general form of sentence disentanglement, targeting the localised modification and control of more general sentence semantic features. To achieve this, we contribute to a novel notion of sentence semantic disentanglement and introduce a flow-based invertible neural network (INN) mechanism integrated with a transformer-based language Autoencoder (AE) in order to deliver latent spaces with better separability properties. Experimental results demonstrate that the model can conform the distributed latent space into a better semantically disentangled sentence space, leading to improved language interpretability and controlled generation when compared to the recent state-of-the-art language VAE models.

翻译：解耦隐空间通常具有更好的语义可分性和几何特性，从而带来更强的可解释性和更可控的数据生成能力。虽然这在计算机视觉领域（如图像解耦任务）中已得到充分研究，但在自然语言处理领域的句子解耦方面仍相对薄弱。以往研究多聚焦于风格迁移场景下（如情感等）任务特异性生成因子的解耦。本文聚焦于更通用的句子解耦形式，旨在实现一般性句子语义特征的局部修改与调控。为此，我们提出了一种新颖的句子语义解耦范式，并引入基于流的可逆神经网络（INN）机制与基于Transformer的语言自编码器（AE）相融合，以构建具有更优可分离特性的隐空间。实验结果表明，该模型能将分散的隐空间转化为语义解耦更优的句子空间，相比当前最先进的语言VAE模型，显著提升了语言可解释性与可控生成能力。