Bag-of-Vectors Autoencoders for Unsupervised Conditional Text Generation

Abstract

Text autoencoders are often used for unsupervised conditional text generation by applying mappings in the latent space to change attributes to the desired values. Recently, Mai et al. (2020) proposed Emb2Emb, a method to learn these mappings in the embedding space of an autoencoder. However, their method is restricted to autoencoders with a single-vector embedding, which limits how much information can be retained. We address this issue by extending their method to Bag-of-Vectors Autoencoders (BoV-AEs), which encode the text into a variable-size bag of vectors that grows with the size of the text, as in attention-based models. This allows to encode and reconstruct much longer texts than standard autoencoders. Analogous to conventional autoencoders, we propose regularization techniques that facilitate learning meaningful operations in the latent space. Finally, we adapt Emb2Emb for a training scheme that learns to map an input bag to an output bag, including a novel loss function and neural architecture. Our empirical evaluations on unsupervised sentiment transfer show that our method performs substantially better than a standard autoencoder.

arXiv commentPublished at AACL 2022

References in corpus (8)

• On the Opportunities and Risks of Foundation Models
• Zero-Shot Text-to-Image Generation
• CTRL: A Conditional Transformer Language Model for Controllable Generation
• Style Transfer from Non-Parallel Text by Cross-Alignment
• Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
• Learning and Evaluating General Linguistic Intelligence
• Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation
• SummAE: Zero-Shot Abstractive Text Summarization using Length-Agnostic Auto-Encoders